Rice Yield Prediction Based on Simulation Zone Partitioning and Dual-Variable Hierarchical Assimilation

Data assimilation can be used to predict crop yield by coupling remote sensing information with the crop growth model, but it often grapples with the challenge of enhancing the computational efficiency for the integrated model. To address this issue, particularly in regional-scale studies, simulatio...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Remote sensing (Basel, Switzerland) Ročník 17; číslo 3; s. 386
Hlavní autoři: He, Jiaoyang, Zhao, Yanxi, He, Ping, Yu, Minglei, Zhu, Yan, Cao, Weixing, Zhang, Xiaohu, Tian, Yongchao
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.02.2025
Témata:
Agricultural production
Algorithms
Analysis
Climate change
Clustering
Coefficient of variation
Computational efficiency
Computer applications
Crop growth
Crop yield
Crop yields
Crops
Data collection
Efficiency
Food supply
Growth models
hierarchical assimilation
Landsat satellites
Leaf area
Leaf area index
Partitioning
Plant extracts
Precipitation
Predictions
Regions
Remote sensing
Rice
RiceGrow
Simulation
simulation zone partitioning
Soil sciences
State variable
Vegetation
Wheat
yield
Jiangsu China
China
ISSN:2072-4292, 2072-4292
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Data assimilation can be used to predict crop yield by coupling remote sensing information with the crop growth model, but it often grapples with the challenge of enhancing the computational efficiency for the integrated model. To address this issue, particularly in regional-scale studies, simulation zone partitioning can offer a viable solution to improve computational efficiency. In this study, we first extracted high-resolution rice planting areas in Jiangsu Province (JP), then conducted simulation zone partitioning in JP based on the fuzzy c-means clustering algorithm (FCM) combined with soil data, meteorological indices, and EVI. Finally, the hierarchical assimilation system was developed by using phenology and leaf area index (LAI) as state variables to predict rice yield in JP. The results showed that the coefficient of variation (CV) of the small subregion after simulation zone partitioning obtained by using FCM was less than the overall CV of each subregion at different period. Compared with a single assimilation system that only used LAI as the state variable (R2 was between 0.33 and 0.35, NRMSE was between 9.08 and 10.94%), the predicted yield of the hierarchical assimilation system (R2 was between 0.44 and 0.51, NRMSE was between 7.23 and 8.44%) was in better agreement with the statistic yield. The research findings can provide technical support for the prediction of rice yield at the regional scale.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2072-4292
2072-4292
DOI:10.3390/rs17030386