Nationwide operational mapping of grassland first mowing dates combining machine learning and Sentinel-2 time series
Grassland dynamics are modulated by management intensity and impact overall ecosystem functioning. In mowed grasslands, the first mowing date is a key indicator of management intensification. The aim of this work was to assess several supervised regression models for mapping grassland first mowing d...
Uložené v:
| Vydané v: | Remote sensing of environment Ročník 315; s. 114476 |
|---|---|
| Hlavní autori: | , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier Inc
15.12.2024
Elsevier |
| Predmet: | |
| ISSN: | 0034-4257, 1879-0704 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Grassland dynamics are modulated by management intensity and impact overall ecosystem functioning. In mowed grasslands, the first mowing date is a key indicator of management intensification. The aim of this work was to assess several supervised regression models for mapping grassland first mowing date at national-level using Sentinel-2 time series. Three deep-learning architectures, two conventional machine learning models and two threshold-based methods (fixed and relative) were compared. Algorithms were trained/calibrated and tested from field observations, using a spatial cross-validation approach. Our findings showed that time aware deep-learning models – Lightweight Temporal Attention Encoder (LTAE) and 1D Convolutional Neural Network (1D-CNN) – yielded higher performances compared to Multilayer Perceptron, Random Forest and Ridge Regression models. Threshold-based methods under-performed compared to all other models. Best model (LTAE) mean absolute error was within six days with a coefficient of determination of 0.52. Additionally, errors were accentuated at extreme (late/early) mowing dates, which were underrepresented in the data set. Oversampling techniques did not improve predicting extreme mowing dates. Finally, the best prediction accuracy was obtained when the number of clear dates surrounding the mowing event was greater than 2. Our outputs evidenced time aware deep-learning models’ potential for large-scale grassland first mowing event monitoring. A national-level map was produced to support bird-life monitoring or public policies for biodiversity and agro-ecological transition in France.
[Display omitted]
•Estimation of grassland first mowing date using regression algorithm.•Time aware deep-learning architectures were the most accurate models.•Threshold-based methods under-performed compared to all supervised models.•LTAE performed reliably across all unknown sites, demonstrating transferability.•Oversampling techniques did not improve predictions accuracy of extreme mowing dates. |
|---|---|
| AbstractList | Grasslands cover approximately 40% of the Earth's land area, encompassing nearly 70% of the global agricultural land area, and are distributed on all continents and across all latitudes (Suttie et al., 2005; White et al., 2000). Grassland dynamics influence global ecosystem functioning, and their impact is widely modulated by management practices intensity on these landscapes (Zhao et al., 2020). Management practices are primarily driven by grassland landscape maintenance, as well as by ecosystem service of provisioning offered by the grasslands. Grasslands are subject to management practices such as mowing or grazing or a combination of both. Therefore, monitoring grassland management practices is essential for assessing management intensity level, which in turn plays a critical role in studies related to biodiversity (XXXX), water (XXXXX) and carbon (XXXXX) cycling and others topics (XXXX). In France, the National Observatory of Mowed Grassland Ecosystems conducts birdlife monitoring in mowed grasslands, with a particular focus on the rise in breeding failures attributed to increasingly early mowing. Early mowing intercepts birds' reproductive period and interrupts their breeding process (Broyer et al., 2012). Usually, responsible agencies conduct occasional observation campaigns to support ecosystem-related public policies, but ground observations are not spatially exhaustive and are time-consuming. As an alternative source, synoptic remote sensing data enables regular and global-scale monitoring, enabling tracking of vegetation dynamics. Currently, Sentinel-2 mission provides cost-free high resolution data at 10m spatial resolution with a 5-day temporal frequency (10 days before 2017), allowing intra-plot level observations. Grassland mowing events timing and intensity have already been mapped using remote sensing-based time series, mainly from features sensitive to vegetation status, such as Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Leaf Area Index (LAI) and more. There have been several methods used to detect mowing events from satellite time series. These methods were mainly based on temporal changes in time series using threshold-based methods and anomalies detection approach. More recently, deep learning-based architectures were also used to detect mowing events timing. Estel et al. (2018) assessed grassland use intensity spatial patterns across Europe. To extract annual mowing frequency, a temporal change analysis based on spline-adjusted MODIS NDVI time series was used. Their approach involved identifying mowing events as instances where a local minima exhibited a change, relative to its preceding peak, exceeding 10% of growing season amplitude. The results showed an overall accuracy of 80%, which decreases as the frequency of events increases. In northern Switzerland, Kolecka et al. (2018) also estimated mowing frequency employing similar temporal change analysis, but based on raw Sentinel-2 NDVI time series. Here, a drop in NDVI greater than 0.2, between two consecutive cloud-free acquisition dates, was counted as a mowing event. Their method accurately identified 77% of observed events and highlighted that false detection can occur due to residual cloud presence, while sparse time series led to the omission of mowing events. Regarding Griffiths et al. (2020), mowing events frequency and timing were mapped in Germany using 10-day composite Harmonized Landsat-Sentinel NDVI time series. Discrepancies between a hypothetical bell-shaped curve and the current polynomial-fitted curve were evaluated. An event was counted when the difference exceeded 0.2 NDVI. Findings revealed consistent spatial patterns in mowing frequency (indicating extensive and intensive management). However, estimated dates exhibited significant discrepancies compared to observed dates (MAE > 50 days), which could be due to lower temporal resolution of Sentinel-2 before 2017 and the absence of reliable ground data for calibration and validation. Stumpf et al. (2020) mapped grassland management (grazing or mowing) and its intensity based on biomass productivity and management frequency, respectively. The latter were extracted from n-day composite Landsat ETM + and Landsat OLI NDVI time series. As in previous cases, a management event was counted when NDVI loss is higher than a threshold, which was based on the probability density function of all NDVI changes across the time series and was specified for p = 0.01. Their approach yielded management patterns consistent with several management-related indicators (species richness, nutrient supply, slope, etc). Recently, Watzig et al. (2023) estimated mowing events in Austria, using Sentinel-2 NDVI time series and implementing discrepancy analysis between a idealized unmowed trajectory and actual NDVI values. An event was recorded if the difference exceeded-0.061. Commission errors due to residual clouds were reduced via a subsequent binary classification of each estimated event using a gradient boosting algorithm trained over cloudy plots. Findings indicated an overall accuracy of 80% in correct event detection, with estimated dates closely aligning with observed dates (MAE < 5 days). Vroey et al. (2022) developed a algorithm for detecting mowing events across Europe. Here, raw Sentinel-2 NDVI and Sentinel-1 VH-coherence time series were used separately. Grassland dynamics are modulated by management intensity and impact overall ecosystem functioning. In mowed grasslands, the first mowing date is a key indicator of management intensification. The aim of this work was to assess several supervised regression models for mapping grassland first mowing date at national-level using Sentinel-2 time series. Three deep-learning architectures, two conventional machine learning models and two threshold-based methods (fixed and relative) were compared. Algorithms were trained/calibrated and tested from field observations, using a spatial cross-validation approach. Our findings showed that time aware deep-learning models – Lightweight Temporal Attention Encoder (LTAE) and 1D Convolutional Neural Network (1D-CNN) – yielded higher performances compared to Multilayer Perceptron, Random Forest and Ridge Regression models. Threshold-based methods under-performed compared to all other models. Best model (LTAE) mean absolute error was within six days with a coefficient of determination of 0.52. Additionally, errors were accentuated at extreme (late/early) mowing dates, which were underrepresented in the data set. Oversampling techniques did not improve predicting extreme mowing dates. Finally, the best prediction accuracy was obtained when the number of clear dates surrounding the mowing event was greater than 2. Our outputs evidenced time aware deep-learning models’ potential for large-scale grassland first mowing event monitoring. A national-level map was produced to support bird-life monitoring or public policies for biodiversity and agro-ecological transition in France. Grassland dynamics are modulated by management intensity and impact overall ecosystem functioning. In mowed grasslands, the first mowing date is a key indicator of management intensification. The aim of this work was to assess several supervised regression models for mapping grassland first mowing date at national-level using Sentinel-2 time series. Three deep-learning architectures, two conventional machine learning models and two threshold-based methods (fixed and relative) were compared. Algorithms were trained/calibrated and tested from field observations, using a spatial cross-validation approach. Our findings showed that time aware deep-learning models – Lightweight Temporal Attention Encoder (LTAE) and 1D Convolutional Neural Network (1D-CNN) – yielded higher performances compared to Multilayer Perceptron, Random Forest and Ridge Regression models. Threshold-based methods under-performed compared to all other models. Best model (LTAE) mean absolute error was within six days with a coefficient of determination of 0.52. Additionally, errors were accentuated at extreme (late/early) mowing dates, which were underrepresented in the data set. Oversampling techniques did not improve predicting extreme mowing dates. Finally, the best prediction accuracy was obtained when the number of clear dates surrounding the mowing event was greater than 2. Our outputs evidenced time aware deep-learning models’ potential for large-scale grassland first mowing event monitoring. A national-level map was produced to support bird-life monitoring or public policies for biodiversity and agro-ecological transition in France. [Display omitted] •Estimation of grassland first mowing date using regression algorithm.•Time aware deep-learning architectures were the most accurate models.•Threshold-based methods under-performed compared to all supervised models.•LTAE performed reliably across all unknown sites, demonstrating transferability.•Oversampling techniques did not improve predictions accuracy of extreme mowing dates. |
| ArticleNumber | 114476 |
| Author | Curtet, Laurence Rivas, Henry Touchais, Hélène Millet, Jerome Fauvel, Mathieu Thierion, Vincent |
| Author_xml | – sequence: 1 givenname: Henry surname: Rivas fullname: Rivas, Henry organization: Centre d’Etudes Spatiales de la Biosphère (CESBIO), Université de Toulouse, CNES/CNRS/INRAE/IRD/UT3-Paul Sabatier, 31401, Toulouse, France – sequence: 2 givenname: Hélène orcidid: 0000-0003-1324-8542 surname: Touchais fullname: Touchais, Hélène organization: Centre d’Etudes Spatiales de la Biosphère (CESBIO), Université de Toulouse, CNES/CNRS/INRAE/IRD/UT3-Paul Sabatier, 31401, Toulouse, France – sequence: 3 givenname: Vincent orcidid: 0000-0001-7965-9833 surname: Thierion fullname: Thierion, Vincent organization: Centre d’Etudes Spatiales de la Biosphère (CESBIO), Université de Toulouse, CNES/CNRS/INRAE/IRD/UT3-Paul Sabatier, 31401, Toulouse, France – sequence: 4 givenname: Jerome orcidid: 0000-0001-5724-2180 surname: Millet fullname: Millet, Jerome organization: Office Français de la Biodiversité (OFB), Direction de la Recherche et de l’Appui Scientifique, 79360, Villiers-en-Bois, France – sequence: 5 givenname: Laurence orcidid: 0000-0002-8792-5983 surname: Curtet fullname: Curtet, Laurence organization: Office Français de la Biodiversité (OFB), Direction de la Recherche et de l’Appui Scientifique, 01330, Montfort, Birieux, France – sequence: 6 givenname: Mathieu orcidid: 0000-0002-3304-6932 surname: Fauvel fullname: Fauvel, Mathieu email: mathieu.fauvel@inrae.fr organization: Centre d’Etudes Spatiales de la Biosphère (CESBIO), Université de Toulouse, CNES/CNRS/INRAE/IRD/UT3-Paul Sabatier, 31401, Toulouse, France |
| BackLink | https://hal.inrae.fr/hal-04775044$$DView record in HAL |
| BookMark | eNp9kUFv1DAQhS1UJLaFH8DNRzhkayfjeCNOVUUp0goOwNmadSatV4kdbLdV_z3OBi4cerLm-X0j-71zduaDJ8beS7GVQraXx21MtK1FDVspAXT7im3kTneV0ALO2EaIBiqolX7DzlM6CiHVTssNy98wu-CfXE88zBRPE458wnl2_o6Hgd9FTGlE3_PBxZT5FJ6Wmx4zJW7DdHB-mSe0984THwnjSViIH-RzEceq5tlNxBNFR-ktez3gmOjd3_OC_br5_PP6ttp___L1-mpf2aaFXNlOdj3W9gCi7xFbCV2jtbKobNEkQQO7AwydaluSu7pXCjuN9QG6dlBDB80F-7juvcfRzNFNGJ9NQGdur_Zm0QSUfQLgURbvh9U7x_D7gVI2k0uWxvJxCg_JNFLBklktilWvVhtDSpEGY10-BZcjutFIYZZOzNGUTszSiVk7KaT8j_z3qpeYTytDJalHR9Ek68hb6l0km00f3Av0H6W4p1s |
| CitedBy_id | crossref_primary_10_3390_rs17183190 crossref_primary_10_1016_j_compag_2025_110613 |
| Cites_doi | 10.1016/j.rse.2018.11.014 10.1007/978-0-387-21606-5 10.1007/s10336-011-0799-6 10.1016/j.rse.2019.03.017 10.1016/j.rse.2018.11.032 10.1016/j.rse.2021.112751 10.1109/TGRS.2023.3234527 10.1080/01431169608948714 10.1007/s10980-020-00980-3 10.1038/s41598-022-04932-6 10.3390/rs14071647 10.3390/rs9060629 10.1016/j.rse.2023.113577 10.3390/su13020471 10.3390/rs10081221 10.5194/bg-21-473-2024 10.1016/j.rse.2021.112795 10.1016/j.isprsjprs.2016.01.011 10.1109/ACCESS.2019.2939152 10.1016/j.rse.2023.113680 10.1155/2013/329187 10.1109/JSTARS.2024.3358066 10.3390/rs11050523 10.1016/j.isprsjprs.2017.07.014 10.3390/rs12121949 10.1016/j.rse.2019.111536 10.1613/jair.953 10.1002/ece3.6957 10.1088/1748-9326/aacc7a 10.3390/electronics10233004 10.1016/0273-1177(89)90481-X 10.1109/LGRS.2017.2681128 10.3390/rs13224668 10.1016/j.ecolind.2020.106201 10.1038/s41592-019-0686-2 10.4000/cybergeo.23155 10.1002/ecs2.2582 10.3390/rs9010095 10.3390/rs15030827 10.1016/j.isprsjprs.2020.12.010 10.1038/nature14539 10.1111/icad.12186 10.3390/rs12050832 |
| ContentType | Journal Article |
| Copyright | 2024 The Authors Attribution - NonCommercial |
| Copyright_xml | – notice: 2024 The Authors – notice: Attribution - NonCommercial |
| DBID | 6I. AAFTH AAYXX CITATION 7S9 L.6 1XC VOOES |
| DOI | 10.1016/j.rse.2024.114476 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef AGRICOLA AGRICOLA - Academic Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access) |
| DatabaseTitle | CrossRef AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Geography Geology Environmental Sciences Statistics |
| EISSN | 1879-0704 |
| ExternalDocumentID | oai:HAL:hal-04775044v1 10_1016_j_rse_2024_114476 S0034425724005029 |
| GeographicLocations | France |
| GeographicLocations_xml | – name: France |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 123 1B1 1RT 1~. 1~5 4.4 457 4G. 53G 5VS 6I. 7-5 71M 8P~ 9JM 9JN AABNK AACTN AAEDT AAEDW AAFTH AAHBH AAIKJ AAKOC AALRI AAOAW AAQFI AAXKI AAXUO ABFNM ABFYP ABJNI ABLST ABMAC ABPPZ ABQEM ABQYD ACDAQ ACGFS ACIWK ACLVX ACPRK ACRLP ACSBN ADBBV ADEZE ADVLN AEBSH AEKER AENEX AFJKZ AFKWA AFRAH AFTJW AFXIZ AGHFR AGUBO AGYEJ AHEUO AHHHB AIEXJ AIKHN AITUG AJOXV AKIFW AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ATOGT AXJTR BKOJK BLECG BLXMC CS3 DU5 EBS EFJIC EO8 EO9 EP2 EP3 FDB FIRID FNPLU FYGXN G-Q GBLVA IHE IMUCA J1W KCYFY KOM LY3 LY9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 RNS ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SSE SSJ SSZ T5K TN5 TWZ WH7 ZCA ZMT ~02 ~G- ~KM 29P 41~ 6TJ 9DU AAQXK AATTM AAYWO AAYXX ABDPE ABEFU ABUFD ABWVN ABXDB ACLOT ACRPL ACVFH ADCNI ADMUD ADNMO ADXHL AEGFY AEIPS AEUPX AFFNX AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EFLBG EJD FA8 FEDTE FGOYB G-2 HMA HMC HVGLF HZ~ H~9 OHT R2- SEN SEP VOH WUQ XOL ~HD 7S9 L.6 1XC VOOES |
| ID | FETCH-LOGICAL-c364t-c919da2cb40ddaa61493775ca5ccb41e4348b4f9566e182d55a97a2b496f5f943 |
| ISICitedReferencesCount | 4 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001348420400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0034-4257 |
| IngestDate | Sat Oct 25 06:38:23 EDT 2025 Wed Oct 01 13:12:49 EDT 2025 Sat Nov 29 06:00:38 EST 2025 Tue Nov 18 22:14:21 EST 2025 Sat Dec 28 15:52:31 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Mowing dates mapping Satellite image time series Regression Deep-learning models Grassland management intensification |
| Language | English |
| License | This is an open access article under the CC BY-NC license. Attribution - NonCommercial: http://creativecommons.org/licenses/by-nc |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c364t-c919da2cb40ddaa61493775ca5ccb41e4348b4f9566e182d55a97a2b496f5f943 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0003-1324-8542 0000-0001-5724-2180 0000-0001-7965-9833 0000-0002-3304-6932 0000-0002-8792-5983 |
| OpenAccessLink | https://hal.inrae.fr/hal-04775044 |
| PQID | 3154158720 |
| PQPubID | 24069 |
| ParticipantIDs | hal_primary_oai_HAL_hal_04775044v1 proquest_miscellaneous_3154158720 crossref_citationtrail_10_1016_j_rse_2024_114476 crossref_primary_10_1016_j_rse_2024_114476 elsevier_sciencedirect_doi_10_1016_j_rse_2024_114476 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-12-15 |
| PublicationDateYYYYMMDD | 2024-12-15 |
| PublicationDate_xml | – month: 12 year: 2024 text: 2024-12-15 day: 15 |
| PublicationDecade | 2020 |
| PublicationTitle | Remote sensing of environment |
| PublicationYear | 2024 |
| Publisher | Elsevier Inc Elsevier |
| Publisher_xml | – name: Elsevier Inc – name: Elsevier |
| References | Ivanda, Šerić, Bugarić, Braović (b25) 2021; 10 Virtanen, Gommers, Oliphant, Haberland, Reddy, Cournapeau, Burovski, Peterson, Weckesser, Bright, van der Walt, Brett, Wilson, Millman, Mayorov, Nelson, Jones, Kern, Larson, Carey, Polat, Feng, Moore, VanderPlas, Laxalde, Perktold, Cimrman, Henriksen, Quintero, Harris, Archibald, Ribeiro, Pedregosa, van Mulbregt, SciPy 1.0 Contributors (b58) 2020; 17 Kussul, Lavreniuk, Skakun, Shelestov (b34) 2017; 14 Mohammed, Rawashdeh, Abdullah (b44) 2020 Liao, Wang, Xie, Baz, Huang, Shang, He (b38) 2020; 12 Buri, Humbert, Stańska, Hajdamowicz, Tran, Entling, Arlettaz (b7) 2016 Inglada, Vincent, Arias, Tardy, Morin, Rodes (b24) 2017; 9 Rouse, Haas, Schell, Deering (b52) 1974; 351 Escadafal (b11) 1989; 9 Estel, Mader, Levers, Verburg, Baumann, Kuemmerle (b12) 2018 Kattenborn, Leitloff, Schiefer, Hinz (b28) 2021; 173 Pontius, Jr. (b48) 2022 Hao, Liu, Yang, Yin, Zhang, Li (b18) 2023; 15 Zhao, Liu, Wu (b68) 2020; 35 Zhong, Hu, Zhou (b69) 2019; 221 Broyer, Curtet, Boissenin (b6) 2012; 153 Kooistra, Berger, Brede, Graf, Aasen, Roujean, Machwitz, Schlerf, Atzberger, Prikaziuk, Ganeva, Tomelleri, Croft, Reyes Muñoz, Garcia Millan, Darvishzadeh, Koren, Herrmann, Rozenstein, Belda, Rautiainen, Rune Karlsen, Figueira Silva, Cerasoli, Pierre, Tanır Kayıkçı, Halabuk, Tunc Gormus, Fluit, Cai, Kycko, Udelhoven, Verrelst (b33) 2024; 21 Suttie, Reynolds, Batello (b55) 2005 Vinayak, Lee, Gedem (b57) 2021; 13 Stumpf, Schneider, Keller, Mayr, Rentschler, Meuli, Schaepman, Liebisch (b54) 2020 Zhang, Luo, Li (b65) 2024; 9 Yang, Tilman, Furey, Lehman (b63) 2019 White, Murray, Rohweder, Prince, Thompson (b62) 2000 Holtgrave, Lobert, Erasmi, Röder, Kleinschmit (b21) 2023 Komisarenko, Voormansik, Elshawi, Sakr (b32) 2022 Garnot, Landrieu (b15) 2020 Zhang, Pan, Li, Gardiner, Sargent, Hare, Atkinson (b66) 2018; 140 Chawla, Bowyer, Hall, Kegelmeyer (b9) 2002 Kingma, D., Ba, J., 2015. Adam: A Method for Stochastic Optimization. In: International Conference on Learning Representations. ICLR, San Diego, CA, USA. Joly, Brossard, Cardot, Cavailhes, Hilal, Wavresky (b27) 2010 Reinermann, Gessner, Asam, Ullmann, Schucknecht, Kuenzer (b51) 2022; 14 Huang, Zhan, Yan, Wu, Deng (b22) 2013 Reinermann, Asam, Kuenzer (b50) 2020 Garioud, Giordano, Valero, Mallet (b14) 2019 Pelletier, Webb, Petitjean (b47) 2019; 11 Team (b56) 2023 Lemaître, Nogueira, Aridas (b36) 2017; 18 Klein, Theux, Arlettaz, Jacot, Pradervand (b30) 2020 Breiman (b5) 2001 Lobert, Holtgrave, Schwieder, Pause, Vogt, Gocht, Erasmi (b40) 2021 Zhang, Lipton, Li, Smola (b64) 2023 Dumeur, Valero, Inglada (b10) 2024; 17 Inglada, Vincent, Arias, Tardy (b23) 2016 LeCun, Bengio, Hinton (b35) 2015 Rahman, Prasetiyowati, Sibaroni (b49) 2023 Lonjou, Desjardins, Hagolle, Petrucci, Tremas, Dejus, Makarau, Auer (b41) 2016; vol. 10001 Belgiu, Drăguţ (b1) 2016; 114 Lin, Zhong, Wang, Xu, Xu, Ying, Rodríguez, Ting, Li (b39) 2020 Vroey, Vendictis, Zavagli, Bontemps, Heymans, Radoux, Koetz, Defourny (b59) 2022 Wang, Li, Tang, Wang, Guga, Bai, Baoyin (b60) 2019 Guidici, Clark (b17) 2017; 9 Kolecka, Ginzler, Pazúr, Price, Verburg (b31) 2018 Li, Chen, Zhang (b37) 2019; 7 Schwieder, Wesemeyer, Frantz, Pfoch, Erasmi, Pickert, Nendel, Hostert (b53) 2022 Ofori-Ampofo, Pelletier, Lang (b45) 2021; 13 Fauvel, Lopes, Dubo, Rivers-Moore, Frison, Gross, Ouin (b13) 2020; 237 Bellet, Fauvel, Inglada (b2) 2023 Bengtsson, Bullock, Egoh, Everson, Everson, O’Connor, O’Farrell, Smith, Lindborg (b4) 2019 Cantelaube, Carles (b8) 2014 Griffiths, Nendel, Pickert, Hostert (b16) 2020 He, Bai, Garcia, Li (b20) 2008 Hastie, Tibshirani, Friedman (b19) 2001 Bellet, Fauvel, Inglada, Michel (b3) 2023 McFeeters (b42) 1996 Pedregosa, Varoquaux, Gramfort, Michel, Thirion, Grisel, Blondel, Prettenhofer, Weiss, Dubourg, Vanderplas, Passos, Cournapeau, Brucher, Perrot, Duchesnay (b46) 2011; 12 Zhang, Sargent, Pan, Li, Gardiner, Hare, Atkinson (b67) 2019; 221 Jafarigol, Trafalis (b26) 2023 Metera, Sakowski, Sloniewski, Romanowicz (b43) 2010; 28 Watzig, Schaumberger, Klingler, Dujakovic, Atzberger, Vuolo (b61) 2023 Guidici (10.1016/j.rse.2024.114476_b17) 2017; 9 McFeeters (10.1016/j.rse.2024.114476_b42) 1996 Zhong (10.1016/j.rse.2024.114476_b69) 2019; 221 Belgiu (10.1016/j.rse.2024.114476_b1) 2016; 114 Hao (10.1016/j.rse.2024.114476_b18) 2023; 15 Bellet (10.1016/j.rse.2024.114476_b3) 2023 Lonjou (10.1016/j.rse.2024.114476_b41) 2016; vol. 10001 He (10.1016/j.rse.2024.114476_b20) 2008 Stumpf (10.1016/j.rse.2024.114476_b54) 2020 Dumeur (10.1016/j.rse.2024.114476_b10) 2024; 17 Li (10.1016/j.rse.2024.114476_b37) 2019; 7 Virtanen (10.1016/j.rse.2024.114476_b58) 2020; 17 Griffiths (10.1016/j.rse.2024.114476_b16) 2020 Metera (10.1016/j.rse.2024.114476_b43) 2010; 28 Ivanda (10.1016/j.rse.2024.114476_b25) 2021; 10 Buri (10.1016/j.rse.2024.114476_b7) 2016 10.1016/j.rse.2024.114476_b29 Zhang (10.1016/j.rse.2024.114476_b67) 2019; 221 Komisarenko (10.1016/j.rse.2024.114476_b32) 2022 Mohammed (10.1016/j.rse.2024.114476_b44) 2020 Garnot (10.1016/j.rse.2024.114476_b15) 2020 Klein (10.1016/j.rse.2024.114476_b30) 2020 Pedregosa (10.1016/j.rse.2024.114476_b46) 2011; 12 Fauvel (10.1016/j.rse.2024.114476_b13) 2020; 237 Garioud (10.1016/j.rse.2024.114476_b14) 2019 Reinermann (10.1016/j.rse.2024.114476_b50) 2020 Pelletier (10.1016/j.rse.2024.114476_b47) 2019; 11 Yang (10.1016/j.rse.2024.114476_b63) 2019 Rahman (10.1016/j.rse.2024.114476_b49) 2023 Breiman (10.1016/j.rse.2024.114476_b5) 2001 Kolecka (10.1016/j.rse.2024.114476_b31) 2018 Cantelaube (10.1016/j.rse.2024.114476_b8) 2014 Escadafal (10.1016/j.rse.2024.114476_b11) 1989; 9 Rouse (10.1016/j.rse.2024.114476_b52) 1974; 351 Joly (10.1016/j.rse.2024.114476_b27) 2010 Lemaître (10.1016/j.rse.2024.114476_b36) 2017; 18 Inglada (10.1016/j.rse.2024.114476_b23) 2016 Vroey (10.1016/j.rse.2024.114476_b59) 2022 Team (10.1016/j.rse.2024.114476_b56) 2023 Zhang (10.1016/j.rse.2024.114476_b66) 2018; 140 Kattenborn (10.1016/j.rse.2024.114476_b28) 2021; 173 Estel (10.1016/j.rse.2024.114476_b12) 2018 Hastie (10.1016/j.rse.2024.114476_b19) 2001 Chawla (10.1016/j.rse.2024.114476_b9) 2002 LeCun (10.1016/j.rse.2024.114476_b35) 2015 Lin (10.1016/j.rse.2024.114476_b39) 2020 Vinayak (10.1016/j.rse.2024.114476_b57) 2021; 13 Wang (10.1016/j.rse.2024.114476_b60) 2019 Zhang (10.1016/j.rse.2024.114476_b65) 2024; 9 Pontius, Jr. (10.1016/j.rse.2024.114476_b48) 2022 Inglada (10.1016/j.rse.2024.114476_b24) 2017; 9 Holtgrave (10.1016/j.rse.2024.114476_b21) 2023 Kussul (10.1016/j.rse.2024.114476_b34) 2017; 14 Huang (10.1016/j.rse.2024.114476_b22) 2013 Schwieder (10.1016/j.rse.2024.114476_b53) 2022 Liao (10.1016/j.rse.2024.114476_b38) 2020; 12 Lobert (10.1016/j.rse.2024.114476_b40) 2021 White (10.1016/j.rse.2024.114476_b62) 2000 Suttie (10.1016/j.rse.2024.114476_b55) 2005 Watzig (10.1016/j.rse.2024.114476_b61) 2023 Bellet (10.1016/j.rse.2024.114476_b2) 2023 Broyer (10.1016/j.rse.2024.114476_b6) 2012; 153 Jafarigol (10.1016/j.rse.2024.114476_b26) 2023 Zhao (10.1016/j.rse.2024.114476_b68) 2020; 35 Reinermann (10.1016/j.rse.2024.114476_b51) 2022; 14 Bengtsson (10.1016/j.rse.2024.114476_b4) 2019 Kooistra (10.1016/j.rse.2024.114476_b33) 2024; 21 Ofori-Ampofo (10.1016/j.rse.2024.114476_b45) 2021; 13 Zhang (10.1016/j.rse.2024.114476_b64) 2023 |
| References_xml | – year: 2021 ident: b40 article-title: Mowing event detection in permanent grasslands: Systematic evaluation of input features from sentinel-1, sentinel-2, and landsat 8 time series publication-title: Remote Sens. Environ. – year: 2023 ident: b21 article-title: Grassland mowing event detection using combined optical, SAR, and weather time series publication-title: Remote Sens. Environ. – start-page: 58 year: 2014 end-page: 64 ident: b8 article-title: Le registre parcellaire graphique: des données géographiques pour décrire la couverture du sol agricole publication-title: Cahier Tech. l’INRA – year: 2020 ident: b39 article-title: DeepCropNet: A deep spatial-temporal learning framework for county-level corn yield estimation publication-title: Environ. Res. Lett. – year: 2016 ident: b7 article-title: Delayed mowing promotes planthoppers, leafhoppers and spiders in extensively managed meadows publication-title: Insect Conserv. Divers. – volume: 9 year: 2017 ident: b24 article-title: Operational high resolution land cover map production at the country scale using satellite image time series publication-title: Remote Sens. – volume: 15 year: 2023 ident: b18 article-title: A review of data augmentation methods of remote sensing image target recognition publication-title: Remote Sens. – year: 2023 ident: b49 article-title: Performance analysis of the imbalanced data method on increasing the classification accuracy of the machine learning hybrid method publication-title: Jipi (J. Ilmiah Penelitian Dan Pembelajaran Inform.) – year: 2019 ident: b4 article-title: Grasslands—more important for ecosystem services than you might think publication-title: Ecosphere – year: 2020 ident: b30 article-title: Modeling the effects of grassland management intensity on biodiversity publication-title: Ecol. Evol. – year: 2023 ident: b61 article-title: Grassland cut detection based on sentinel-2 time series to respond to the environmental and technical challenges of the Austrian fodder production for livestock feeding publication-title: Remote Sens. Environ. – year: 2020 ident: b16 article-title: Towards national-scale characterization of grassland use intensity from integrated sentinel-2 and landsat time series publication-title: Remote Sens. Environ. – year: 2018 ident: b31 article-title: Regional scale mapping of grassland mowing frequency with sentinel-2 time series publication-title: Remote Sens. – year: 2022 ident: b53 article-title: Mapping grassland mowing events across Germany based on combined sentinel-2 and landsat 8 time series publication-title: Remote Sens. Environ. – volume: 7 start-page: 134677 year: 2019 end-page: 134690 ident: b37 article-title: Temporal attention networks for multitemporal multisensor crop classification publication-title: IEEE Access – volume: 17 start-page: 261 year: 2020 end-page: 272 ident: b58 article-title: SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python publication-title: Nature Methods – volume: 9 start-page: 629 year: 2017 ident: b17 article-title: One-dimensional convolutional neural network land-cover classification of multi-seasonal hyperspectral imagery in the San Francisco Bay Area, California publication-title: Remote Sens. – volume: 10 start-page: 3004 year: 2021 ident: b25 article-title: Mapping chlorophyll-a concentrations in the Kaštela bay and Brač channel using ridge regression and sentinel-2 satellite images publication-title: Electronics – volume: 9 year: 2024 ident: b65 article-title: Classifying raw irregular time series (CRIT) for large area land cover mapping by adapting transformer model publication-title: Sci. Remote Sens. – year: 2020 ident: b54 article-title: Spatial monitoring of grassland management using multi-temporal satellite imagery publication-title: Ecol. Indic. – year: 2023 ident: b2 article-title: Land Cover Classification with Gaussian Processes using spatio-spectro-temporal features publication-title: IEEE Trans. Geosci. Remote Sens. – year: 2001 ident: b19 article-title: The elements of statistical learning publication-title: Springer Series in Statistics – volume: 13 start-page: 4668 year: 2021 ident: b45 article-title: Crop type mapping from optical and radar time series using attention-based deep learning publication-title: Remote Sens. – year: 2023 ident: b56 article-title: Orfeo ToolBox 8.1.2 – volume: 17 start-page: 4350 year: 2024 end-page: 4367 ident: b10 article-title: Self-supervised spatio-temporal representation learning of satellite image time series publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. – reference: Kingma, D., Ba, J., 2015. Adam: A Method for Stochastic Optimization. In: International Conference on Learning Representations. ICLR, San Diego, CA, USA. – year: 2018 ident: b12 article-title: Combining satellite data and agricultural statistics to map grassland management intensity in europe publication-title: Environ. Res. Lett. – year: 2019 ident: b60 article-title: Land use alters relationships of grassland productivity with plant and arthropod diversity in inner mongolian grassland publication-title: Ecol. Appl. – year: 2020 ident: b50 article-title: Remote sensing of grassland production and management—A review publication-title: Remote Sens. – year: 2010 ident: b27 article-title: Les types de climats en France, une construction spatiale publication-title: Cybergeo: European Journal of Geography – volume: 221 start-page: 430 year: 2019 end-page: 443 ident: b69 article-title: Deep learning based multi-temporal crop classification publication-title: Remote Sens. Environ. – volume: 153 start-page: 817 year: 2012 end-page: 823 ident: b6 article-title: Does breeding success lead meadow passerines to select late mown fields? publication-title: J. Ornithol. – volume: 9 start-page: 159 year: 1989 end-page: 163 ident: b11 article-title: Remote sensing of arid soil surface color with landsat thematic mapper publication-title: Adv. Space Res. – volume: 11 start-page: 523 year: 2019 ident: b47 article-title: Temporal convolutional neural network for the classification of satellite image time series publication-title: Remote Sens. – year: 2005 ident: b55 publication-title: Grasslands of the World – year: 1996 ident: b42 article-title: The use of the normalized difference water index (NDWI) in the delineation of open water features publication-title: Int. J. Remote Sens. – volume: 12 start-page: 2825 year: 2011 end-page: 2830 ident: b46 article-title: Scikit-learn: Machine learning in python publication-title: J. Mach. Learn. Res. – year: 2016 ident: b23 article-title: iota2-a25386 – year: 2015 ident: b35 article-title: Deep learning publication-title: Nature – year: 2001 ident: b5 article-title: Random forests publication-title: Mach. Learn. – year: 2023 ident: b26 article-title: A review of machine learning techniques in imbalanced data and future trends – year: 2022 ident: b48 article-title: Metrics That Make a Difference: How to Analyze Change and Error – volume: 35 start-page: 793 year: 2020 end-page: 814 ident: b68 article-title: Grassland ecosystem services: a systematic review of research advances and future directions publication-title: Landsc. Ecol. – year: 2023 ident: b3 article-title: End-to-end Learning for Land Cover Classification using Irregular and Unaligned SITS by Combining Attention-Based Interpolation with Sparse Variational Gaussian Processes publication-title: IEEE J. Sel Top. Appl. Earth Observ. Remote Sens. – year: 2008 ident: b20 article-title: ADASYN: Adaptive synthetic sampling approach for imbalanced learning publication-title: IEEE International Joint Conference on Neural Networks – volume: 12 start-page: 832 year: 2020 ident: b38 article-title: Synergistic use of multi-temporal RADARSAT-2 and VEN publication-title: Remote Sens. – year: 2000 ident: b62 article-title: Grassland Ecosystems – start-page: 171 year: 2020 end-page: 181 ident: b15 article-title: Lightweight temporal self-attention for classifying satellite images time series publication-title: Advanced Analytics and Learning on Temporal Data – volume: 173 start-page: 24 year: 2021 end-page: 49 ident: b28 article-title: Review on convolutional neural networks (CNN) in vegetation remote sensing publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 221 start-page: 173 year: 2019 end-page: 187 ident: b67 article-title: Joint deep learning for land cover and land use classification publication-title: Remote Sens. Environ. – year: 2002 ident: b9 article-title: SMOTE: Synthetic minority over-sampling technique publication-title: J. Artificial Intelligence Res. – year: 2013 ident: b22 article-title: Evaluation of the impacts of land use on water quality: A case study in the chaohu lake basin publication-title: Sci. World J. – volume: vol. 10001 year: 2016 ident: b41 article-title: MACCS-ATCOR joint algorithm (MAJA) publication-title: Remote Sensing of Clouds and the Atmosphere XXI – volume: 13 start-page: 471 year: 2021 ident: b57 article-title: Prediction of land use and land cover changes in Mumbai city, India, using remote sensing data and a multilayer perceptron neural network-based Markov chain model publication-title: Sustainability – volume: 351 start-page: 309 year: 1974 ident: b52 article-title: Monitoring vegetation systems in the great plains with ERTS publication-title: NASA Spec. Publ. – volume: 140 start-page: 133 year: 2018 end-page: 144 ident: b66 article-title: A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 21 start-page: 473 year: 2024 end-page: 511 ident: b33 article-title: Reviews and syntheses: Remotely sensed optical time series for monitoring vegetation productivity publication-title: Biogeosciences – volume: 18 start-page: 1 year: 2017 end-page: 5 ident: b36 article-title: Imbalanced-learn: A python toolbox to tackle the curse of imbalanced datasets in machine learning publication-title: J. Mach. Learn. Res. – start-page: 243 year: 2020 end-page: 248 ident: b44 article-title: Machine learning with oversampling and undersampling techniques: Overview study and experimental results publication-title: 2020 11th International Conference on Information and Communication Systems – year: 2022 ident: b32 article-title: Exploiting time series of sentinel-1 and sentinel-2 to detect grassland mowing events using deep learning With Reject Region publication-title: Sci. Rep. – year: 2022 ident: b59 article-title: Mowing detection using sentinel-1 and sentinel-2 time series for large scale grassland monitoring publication-title: Remote Sens. Environ. – year: 2019 ident: b63 article-title: Soil carbon sequestration accelerated by restoration of grassland biodiversity publication-title: Nature Commun. – volume: 14 start-page: 778 year: 2017 end-page: 782 ident: b34 article-title: Deep learning classification of land cover and crop types using remote sensing data publication-title: IEEE Geosci. Remote Sens. Lett. – volume: 14 year: 2022 ident: b51 article-title: Detection of grassland mowing events for Germany by combining sentinel-1 and sentinel-2 time series publication-title: Remote Sens. – volume: 114 start-page: 24 year: 2016 end-page: 31 ident: b1 article-title: Random forest in remote sensing: A review of applications and future directions publication-title: ISPRS J. Photogramm. Remote Sens. – start-page: 1 year: 2019 end-page: 4 ident: b14 article-title: Challenges in Grassland Mowing Event Detection with Multimodal Sentinel Images publication-title: 2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp) – volume: 28 start-page: 315 year: 2010 end-page: 334 ident: b43 article-title: Grazing as a tool to maintain biodiversity of grassland - a review publication-title: Animal Sci. Pap. Rep. – year: 2023 ident: b64 article-title: Dive into Deep Learning – volume: 237 year: 2020 ident: b13 article-title: Prediction of plant diversity in grasslands using sentinel-1 and -2 satellite image time series publication-title: Remote Sens. Environ. – volume: 18 start-page: 1 issue: 17 year: 2017 ident: 10.1016/j.rse.2024.114476_b36 article-title: Imbalanced-learn: A python toolbox to tackle the curse of imbalanced datasets in machine learning publication-title: J. Mach. Learn. Res. – volume: 221 start-page: 173 year: 2019 ident: 10.1016/j.rse.2024.114476_b67 article-title: Joint deep learning for land cover and land use classification publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2018.11.014 – year: 2001 ident: 10.1016/j.rse.2024.114476_b19 article-title: The elements of statistical learning doi: 10.1007/978-0-387-21606-5 – year: 2023 ident: 10.1016/j.rse.2024.114476_b49 article-title: Performance analysis of the imbalanced data method on increasing the classification accuracy of the machine learning hybrid method publication-title: Jipi (J. Ilmiah Penelitian Dan Pembelajaran Inform.) – volume: 153 start-page: 817 year: 2012 ident: 10.1016/j.rse.2024.114476_b6 article-title: Does breeding success lead meadow passerines to select late mown fields? publication-title: J. Ornithol. doi: 10.1007/s10336-011-0799-6 – year: 2019 ident: 10.1016/j.rse.2024.114476_b63 article-title: Soil carbon sequestration accelerated by restoration of grassland biodiversity publication-title: Nature Commun. – year: 2020 ident: 10.1016/j.rse.2024.114476_b16 article-title: Towards national-scale characterization of grassland use intensity from integrated sentinel-2 and landsat time series publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2019.03.017 – volume: 221 start-page: 430 year: 2019 ident: 10.1016/j.rse.2024.114476_b69 article-title: Deep learning based multi-temporal crop classification publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2018.11.032 – volume: 12 start-page: 2825 year: 2011 ident: 10.1016/j.rse.2024.114476_b46 article-title: Scikit-learn: Machine learning in python publication-title: J. Mach. Learn. Res. – year: 2021 ident: 10.1016/j.rse.2024.114476_b40 article-title: Mowing event detection in permanent grasslands: Systematic evaluation of input features from sentinel-1, sentinel-2, and landsat 8 time series publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2021.112751 – year: 2023 ident: 10.1016/j.rse.2024.114476_b2 article-title: Land Cover Classification with Gaussian Processes using spatio-spectro-temporal features publication-title: IEEE Trans. Geosci. Remote Sens. doi: 10.1109/TGRS.2023.3234527 – year: 2005 ident: 10.1016/j.rse.2024.114476_b55 – year: 2001 ident: 10.1016/j.rse.2024.114476_b5 article-title: Random forests publication-title: Mach. Learn. – year: 2023 ident: 10.1016/j.rse.2024.114476_b64 – year: 1996 ident: 10.1016/j.rse.2024.114476_b42 article-title: The use of the normalized difference water index (NDWI) in the delineation of open water features publication-title: Int. J. Remote Sens. doi: 10.1080/01431169608948714 – year: 2008 ident: 10.1016/j.rse.2024.114476_b20 article-title: ADASYN: Adaptive synthetic sampling approach for imbalanced learning – ident: 10.1016/j.rse.2024.114476_b29 – volume: 35 start-page: 793 year: 2020 ident: 10.1016/j.rse.2024.114476_b68 article-title: Grassland ecosystem services: a systematic review of research advances and future directions publication-title: Landsc. Ecol. doi: 10.1007/s10980-020-00980-3 – year: 2022 ident: 10.1016/j.rse.2024.114476_b32 article-title: Exploiting time series of sentinel-1 and sentinel-2 to detect grassland mowing events using deep learning With Reject Region publication-title: Sci. Rep. doi: 10.1038/s41598-022-04932-6 – year: 2016 ident: 10.1016/j.rse.2024.114476_b23 – volume: 14 issue: 7 year: 2022 ident: 10.1016/j.rse.2024.114476_b51 article-title: Detection of grassland mowing events for Germany by combining sentinel-1 and sentinel-2 time series publication-title: Remote Sens. doi: 10.3390/rs14071647 – volume: 9 start-page: 629 issue: 6 year: 2017 ident: 10.1016/j.rse.2024.114476_b17 article-title: One-dimensional convolutional neural network land-cover classification of multi-seasonal hyperspectral imagery in the San Francisco Bay Area, California publication-title: Remote Sens. doi: 10.3390/rs9060629 – year: 2023 ident: 10.1016/j.rse.2024.114476_b61 article-title: Grassland cut detection based on sentinel-2 time series to respond to the environmental and technical challenges of the Austrian fodder production for livestock feeding publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2023.113577 – year: 2000 ident: 10.1016/j.rse.2024.114476_b62 – volume: 13 start-page: 471 issue: 2 year: 2021 ident: 10.1016/j.rse.2024.114476_b57 article-title: Prediction of land use and land cover changes in Mumbai city, India, using remote sensing data and a multilayer perceptron neural network-based Markov chain model publication-title: Sustainability doi: 10.3390/su13020471 – year: 2022 ident: 10.1016/j.rse.2024.114476_b59 article-title: Mowing detection using sentinel-1 and sentinel-2 time series for large scale grassland monitoring publication-title: Remote Sens. Environ. – start-page: 1 year: 2019 ident: 10.1016/j.rse.2024.114476_b14 article-title: Challenges in Grassland Mowing Event Detection with Multimodal Sentinel Images – year: 2018 ident: 10.1016/j.rse.2024.114476_b31 article-title: Regional scale mapping of grassland mowing frequency with sentinel-2 time series publication-title: Remote Sens. doi: 10.3390/rs10081221 – volume: 21 start-page: 473 issue: 2 year: 2024 ident: 10.1016/j.rse.2024.114476_b33 article-title: Reviews and syntheses: Remotely sensed optical time series for monitoring vegetation productivity publication-title: Biogeosciences doi: 10.5194/bg-21-473-2024 – year: 2022 ident: 10.1016/j.rse.2024.114476_b53 article-title: Mapping grassland mowing events across Germany based on combined sentinel-2 and landsat 8 time series publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2021.112795 – start-page: 58 year: 2014 ident: 10.1016/j.rse.2024.114476_b8 article-title: Le registre parcellaire graphique: des données géographiques pour décrire la couverture du sol agricole publication-title: Cahier Tech. l’INRA – volume: vol. 10001 year: 2016 ident: 10.1016/j.rse.2024.114476_b41 article-title: MACCS-ATCOR joint algorithm (MAJA) – volume: 351 start-page: 309 issue: 1 year: 1974 ident: 10.1016/j.rse.2024.114476_b52 article-title: Monitoring vegetation systems in the great plains with ERTS publication-title: NASA Spec. Publ. – volume: 114 start-page: 24 year: 2016 ident: 10.1016/j.rse.2024.114476_b1 article-title: Random forest in remote sensing: A review of applications and future directions publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2016.01.011 – volume: 7 start-page: 134677 year: 2019 ident: 10.1016/j.rse.2024.114476_b37 article-title: Temporal attention networks for multitemporal multisensor crop classification publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2939152 – year: 2023 ident: 10.1016/j.rse.2024.114476_b21 article-title: Grassland mowing event detection using combined optical, SAR, and weather time series publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2023.113680 – year: 2013 ident: 10.1016/j.rse.2024.114476_b22 article-title: Evaluation of the impacts of land use on water quality: A case study in the chaohu lake basin publication-title: Sci. World J. doi: 10.1155/2013/329187 – volume: 17 start-page: 4350 year: 2024 ident: 10.1016/j.rse.2024.114476_b10 article-title: Self-supervised spatio-temporal representation learning of satellite image time series publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. doi: 10.1109/JSTARS.2024.3358066 – volume: 11 start-page: 523 issue: 5 year: 2019 ident: 10.1016/j.rse.2024.114476_b47 article-title: Temporal convolutional neural network for the classification of satellite image time series publication-title: Remote Sens. doi: 10.3390/rs11050523 – volume: 140 start-page: 133 year: 2018 ident: 10.1016/j.rse.2024.114476_b66 article-title: A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2017.07.014 – year: 2020 ident: 10.1016/j.rse.2024.114476_b50 article-title: Remote sensing of grassland production and management—A review publication-title: Remote Sens. doi: 10.3390/rs12121949 – volume: 237 year: 2020 ident: 10.1016/j.rse.2024.114476_b13 article-title: Prediction of plant diversity in grasslands using sentinel-1 and -2 satellite image time series publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2019.111536 – year: 2002 ident: 10.1016/j.rse.2024.114476_b9 article-title: SMOTE: Synthetic minority over-sampling technique publication-title: J. Artificial Intelligence Res. doi: 10.1613/jair.953 – year: 2020 ident: 10.1016/j.rse.2024.114476_b30 article-title: Modeling the effects of grassland management intensity on biodiversity publication-title: Ecol. Evol. doi: 10.1002/ece3.6957 – year: 2023 ident: 10.1016/j.rse.2024.114476_b56 – year: 2018 ident: 10.1016/j.rse.2024.114476_b12 article-title: Combining satellite data and agricultural statistics to map grassland management intensity in europe publication-title: Environ. Res. Lett. doi: 10.1088/1748-9326/aacc7a – volume: 9 year: 2024 ident: 10.1016/j.rse.2024.114476_b65 article-title: Classifying raw irregular time series (CRIT) for large area land cover mapping by adapting transformer model publication-title: Sci. Remote Sens. – volume: 10 start-page: 3004 issue: 23 year: 2021 ident: 10.1016/j.rse.2024.114476_b25 article-title: Mapping chlorophyll-a concentrations in the Kaštela bay and Brač channel using ridge regression and sentinel-2 satellite images publication-title: Electronics doi: 10.3390/electronics10233004 – volume: 9 start-page: 159 issue: 1 year: 1989 ident: 10.1016/j.rse.2024.114476_b11 article-title: Remote sensing of arid soil surface color with landsat thematic mapper publication-title: Adv. Space Res. doi: 10.1016/0273-1177(89)90481-X – year: 2023 ident: 10.1016/j.rse.2024.114476_b3 article-title: End-to-end Learning for Land Cover Classification using Irregular and Unaligned SITS by Combining Attention-Based Interpolation with Sparse Variational Gaussian Processes publication-title: IEEE J. Sel Top. Appl. Earth Observ. Remote Sens. – start-page: 171 year: 2020 ident: 10.1016/j.rse.2024.114476_b15 article-title: Lightweight temporal self-attention for classifying satellite images time series – volume: 14 start-page: 778 issue: 5 year: 2017 ident: 10.1016/j.rse.2024.114476_b34 article-title: Deep learning classification of land cover and crop types using remote sensing data publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2017.2681128 – volume: 13 start-page: 4668 issue: 22 year: 2021 ident: 10.1016/j.rse.2024.114476_b45 article-title: Crop type mapping from optical and radar time series using attention-based deep learning publication-title: Remote Sens. doi: 10.3390/rs13224668 – year: 2020 ident: 10.1016/j.rse.2024.114476_b54 article-title: Spatial monitoring of grassland management using multi-temporal satellite imagery publication-title: Ecol. Indic. doi: 10.1016/j.ecolind.2020.106201 – volume: 28 start-page: 315 year: 2010 ident: 10.1016/j.rse.2024.114476_b43 article-title: Grazing as a tool to maintain biodiversity of grassland - a review publication-title: Animal Sci. Pap. Rep. – year: 2022 ident: 10.1016/j.rse.2024.114476_b48 – year: 2023 ident: 10.1016/j.rse.2024.114476_b26 – volume: 17 start-page: 261 year: 2020 ident: 10.1016/j.rse.2024.114476_b58 article-title: SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python publication-title: Nature Methods doi: 10.1038/s41592-019-0686-2 – start-page: 243 year: 2020 ident: 10.1016/j.rse.2024.114476_b44 article-title: Machine learning with oversampling and undersampling techniques: Overview study and experimental results – year: 2010 ident: 10.1016/j.rse.2024.114476_b27 article-title: Les types de climats en France, une construction spatiale publication-title: Cybergeo: European Journal of Geography doi: 10.4000/cybergeo.23155 – year: 2019 ident: 10.1016/j.rse.2024.114476_b4 article-title: Grasslands—more important for ecosystem services than you might think publication-title: Ecosphere doi: 10.1002/ecs2.2582 – volume: 9 issue: 1 year: 2017 ident: 10.1016/j.rse.2024.114476_b24 article-title: Operational high resolution land cover map production at the country scale using satellite image time series publication-title: Remote Sens. doi: 10.3390/rs9010095 – volume: 15 issue: 3 year: 2023 ident: 10.1016/j.rse.2024.114476_b18 article-title: A review of data augmentation methods of remote sensing image target recognition publication-title: Remote Sens. doi: 10.3390/rs15030827 – volume: 173 start-page: 24 year: 2021 ident: 10.1016/j.rse.2024.114476_b28 article-title: Review on convolutional neural networks (CNN) in vegetation remote sensing publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2020.12.010 – year: 2015 ident: 10.1016/j.rse.2024.114476_b35 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – year: 2019 ident: 10.1016/j.rse.2024.114476_b60 article-title: Land use alters relationships of grassland productivity with plant and arthropod diversity in inner mongolian grassland publication-title: Ecol. Appl. – year: 2016 ident: 10.1016/j.rse.2024.114476_b7 article-title: Delayed mowing promotes planthoppers, leafhoppers and spiders in extensively managed meadows publication-title: Insect Conserv. Divers. doi: 10.1111/icad.12186 – volume: 12 start-page: 832 issue: 5 year: 2020 ident: 10.1016/j.rse.2024.114476_b38 article-title: Synergistic use of multi-temporal RADARSAT-2 and VENμS data for crop classification based on 1D convolutional neural network publication-title: Remote Sens. doi: 10.3390/rs12050832 – year: 2020 ident: 10.1016/j.rse.2024.114476_b39 article-title: DeepCropNet: A deep spatial-temporal learning framework for county-level corn yield estimation publication-title: Environ. Res. Lett. |
| SSID | ssj0015871 |
| Score | 2.487021 |
| Snippet | Grassland dynamics are modulated by management intensity and impact overall ecosystem functioning. In mowed grasslands, the first mowing date is a key... Grasslands cover approximately 40% of the Earth's land area, encompassing nearly 70% of the global agricultural land area, and are distributed on all... |
| SourceID | hal proquest crossref elsevier |
| SourceType | Open Access Repository Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 114476 |
| SubjectTerms | agroecology biodiversity data collection Deep-learning models ecosystems environment France Grassland management intensification grasslands Machine Learning Mowing dates mapping neural networks prediction Regression Satellite image time series Statistics time series analysis |
| Title | Nationwide operational mapping of grassland first mowing dates combining machine learning and Sentinel-2 time series |
| URI | https://dx.doi.org/10.1016/j.rse.2024.114476 https://www.proquest.com/docview/3154158720 https://hal.inrae.fr/hal-04775044 |
| Volume | 315 |
| WOSCitedRecordID | wos001348420400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1879-0704 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0015871 issn: 0034-4257 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELfKBmIvCAoT5UsG8UQVlCZOnTxW0K2Dqpq0MvXNch2HdurSql_bn8efxp3tJGXANB54SSO7dpver_ad7-53hLzXOmNa-cqTSmUeiwLuJWkGhmskQ4Y7CDM1ls77fDCIR6PktFb7UeTCbGc8z-Pr62TxX0UNbSBsTJ39B3GXk0ID3IPQ4Qpih-udBG-Zrq-mqW7OF3pZHPZdysXCRTh_X4LGjBGNzWwKyl_zcn6FPWj7rzDGfGyKRsAIjLPURWEJm8t4htFFuZ55gSlL38RHcmGIBc23BuljR75yn7eTTFf6d6Zbm0lmkiSqo-6NmkjLetCzLvyZeYkr5_8Qi3dPbazA-TRXO5OavEbrW9ElC4M70QgMb6LN6bTHbE4n2F22Q-bh4mI3LbtSxxyzr2zt4mIpD-00v20L9oTi4uNyhcyoAUOGZMb_QMHd65yJ089Hon8y-Ppr707cYq_Th-tEzjyfcaTHZ1uwv_cDHiWwru53TrqjL6UnK4q5rdroHqHwrJsYwxvf52-60b0JBune0BWMAjR8TB45y4V2LOKekJrO6-SwW8kWOt1OsaqTh8fakaHXyYNjUz4a7g7QtrHU4E_JukIq3UEqdUil84yWSKUGqdQilRqk0hKp1CGVFkilOKJCKkWkUovUZ-TbUXf4qee5IiCeCtts7amklaQyUGPmp6mUoE2CQs0jJSMFbS3NQhaPWQZmfluDrZxGkUy4DMYsaWdRlrDwkOzl81w_J5SD6gwWcgu0YBCc9hOe-pEP-ljLb6sg0Q3iFz-_UI4hHwu1zEQRCnkhQGICJSasxBrkQzlkYelhbnszK2QqnH5r9VYBOL1t2DuQfzk98sEDAgW2VfhrkLcFPARsEOj1k7meb1YC_hMMURj4L-4y0UtyUP0nX5G99XKjX5P7agvoWL5x6P4JGEvc4g |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Nationwide+operational+mapping+of+grassland+first+mowing+dates+combining+machine+learning+and+Sentinel-2+time+series&rft.jtitle=Remote+sensing+of+environment&rft.au=Rivas%2C+Henry&rft.au=Touchais%2C+H%C3%A9l%C3%A8ne&rft.au=Thierion%2C+Vincent&rft.au=Millet%2C+Jerome&rft.date=2024-12-15&rft.pub=Elsevier&rft.issn=0034-4257&rft.eissn=1879-0704&rft.volume=315&rft_id=info:doi/10.1016%2Fj.rse.2024.114476&rft.externalDBID=HAS_PDF_LINK&rft.externalDocID=oai%3AHAL%3Ahal-04775044v1 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0034-4257&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0034-4257&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0034-4257&client=summon |