Zobraziť v EDS

Assessing NDVI, Climate, and Management to Predict Winter Wheat Yields at Field Scale in Kansas, USA.

Uložené v:
Podrobná bibliografia
Názov: Assessing NDVI, Climate, and Management to Predict Winter Wheat Yields at Field Scale in Kansas, USA.
Autori: Maranhão, Rebecca Lima Albuquerque, Caldas, Marcellus Marques, Kastens, Jude, Watson, Jordan, Lollato, Romulo Pisa
Zdroj: Remote Sensing; Oct2025, Vol. 17 Issue 20, p3500, 27p
Predmety: WINTER wheat, NORMALIZED difference vegetation index, REMOTE sensing, AGRICULTURAL administration, REMOTE sensing devices, ENVIRONMENTAL history, CROP yields
Geografický termín: KANSAS, UNITED States
Abstrakt: Highlights: What are the main findings? Sensor performance and key NDVI stages for winter wheat yield prediction: Landsat USGS, especially during early green-up (DOY 56) and late grain fill (DOY 154) stages, provided the most accurate yield predictions; MODIS also performed reasonably well, while Sentinel-2 was limited by low temporal coverage and cloud contamination. Environmentally dependent yield prediction: Improving yield prediction by incorporating weather and management data with NDVI increased model accuracy, reducing nRMSE from 0.81 (when using only NDVI variables) to 0.51, 0.63, and 0.68 in the W, SC, and NC subregions, respectively. What is the implication of the main finding? Systematic evaluation of different satellite sensors and preprocessing directly impact yield prediction accuracy: future work should optimize preprocessing and best-suited sensors for forecasting. Field-scale yield models should consider the environmental context, integrating weather and management variables where needed, while also providing vegetation index-driven models for more environmentally stable settings to support scalable and context-sensitive forecasting tools. Accurate crop yield prediction is challenging in environmentally diverse areas. This study evaluated the potential of different satellite sensors to predict winter wheat grain yield at the field level in Kansas, the U.S.'s leading winter wheat producer. Using Landsat NDVI data from late February to June, a linear regression model was able to reduce the standard deviation of predicted yields by over 20% (with a normalized root mean square error (nRMSE) of 80%). The NDVI during the anthesis and grain fill stages was essential for precise yield estimation. A subregional approach that incorporated weather and management data improved results, accounting for 51%, 63%, and 68% of the nRMSE in W, SC, and NC. Results indicate that NDVI-based yield models at the field scale are environmentally dependent, particularly in south-central and western Kansas, areas prone to heat stress and water deficit, respectively. Our findings showed the benefits of an environmental subregional model integrating remote sensing and field-specific weather and management data to improve yield prediction accuracy, particularly in large, environmentally diverse regions. [ABSTRACT FROM AUTHOR]
Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáza: Complementary Index
Popis
Abstrakt:Highlights: What are the main findings? Sensor performance and key NDVI stages for winter wheat yield prediction: Landsat USGS, especially during early green-up (DOY 56) and late grain fill (DOY 154) stages, provided the most accurate yield predictions; MODIS also performed reasonably well, while Sentinel-2 was limited by low temporal coverage and cloud contamination. Environmentally dependent yield prediction: Improving yield prediction by incorporating weather and management data with NDVI increased model accuracy, reducing nRMSE from 0.81 (when using only NDVI variables) to 0.51, 0.63, and 0.68 in the W, SC, and NC subregions, respectively. What is the implication of the main finding? Systematic evaluation of different satellite sensors and preprocessing directly impact yield prediction accuracy: future work should optimize preprocessing and best-suited sensors for forecasting. Field-scale yield models should consider the environmental context, integrating weather and management variables where needed, while also providing vegetation index-driven models for more environmentally stable settings to support scalable and context-sensitive forecasting tools. Accurate crop yield prediction is challenging in environmentally diverse areas. This study evaluated the potential of different satellite sensors to predict winter wheat grain yield at the field level in Kansas, the U.S.'s leading winter wheat producer. Using Landsat NDVI data from late February to June, a linear regression model was able to reduce the standard deviation of predicted yields by over 20% (with a normalized root mean square error (nRMSE) of 80%). The NDVI during the anthesis and grain fill stages was essential for precise yield estimation. A subregional approach that incorporated weather and management data improved results, accounting for 51%, 63%, and 68% of the nRMSE in W, SC, and NC. Results indicate that NDVI-based yield models at the field scale are environmentally dependent, particularly in south-central and western Kansas, areas prone to heat stress and water deficit, respectively. Our findings showed the benefits of an environmental subregional model integrating remote sensing and field-specific weather and management data to improve yield prediction accuracy, particularly in large, environmentally diverse regions. [ABSTRACT FROM AUTHOR]
ISSN:20724292
DOI:10.3390/rs17203500