Abstract

Climate change, such as increase in CO2 levels and rising temperatures, can have a significant impact on paddy rice production and increase the uncertainty of yield forecasts. This study aims to employ AI modeling for forecasting paddy rice yield and present the findings of a quantitative analysis to determine its ability to generate stable forecasts under extreme weather conditions, such as heatwaves, low temperatures, and heavy rainfall. Vegetation growth indices from the Moderate Resolution Imaging Spectroradiometer (MODIS) satellite product were utilized. These indices include the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Leaf Area Index (LAI), Fraction of Absorbed Photosynthetically Active Radiation (FPAR), and Near-Infrared Reflectance of vegetation (NIRv). Meteorological variables such as downward solar radiation flux, daily temperature difference, precipitation, relative humidity, and temperature were also used. Over 23 years of experimentation (2000-2022), yields under extreme weather conditions did not exhibit a significant difference from the normal period, with a Mean Absolute Error (MAE) ranging from 0.30 to 0.33 ton/ha, representing a 4-5% error of the average yield. This study presents an AI modeling methodology that enables stable predictions of paddy rice yields, even under extreme weather conditions. Future work should focus on refining input data and optimizing the model by analyzing cases of extreme weather.

Abstract

Climate change, such as increase in CO2 levels and rising temperatures, can have a significant impact on paddy rice production and increase the uncertainty of yield forecasts. This study aims to employ AI modeling for forecasting paddy rice yield and present the findings of a quantitative analysis to determine its ability to generate stable forecasts under extreme weather conditions, such as heatwaves, low temperatures, and heavy rainfall. Vegetation growth indices from the Moderate Resolution Imaging Spectroradiometer (MODIS) satellite product were utilized. These indices include the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Leaf Area Index (LAI), Fraction of Absorbed Photosynthetically Active Radiation (FPAR), and Near-Infrared Reflectance of vegetation (NIRv). Meteorological variables such as downward solar radiation flux, daily temperature difference, precipitation, relative humidity, and temperature were also used. Over 23 years of experimentation (2000-2022), yields under extreme weather conditions did not exhibit a significant difference from the normal period, with a Mean Absolute Error (MAE) ranging from 0.30 to 0.33 ton/ha, representing a 4-5% error of the average yield. This study presents an AI modeling methodology that enables stable predictions of paddy rice yields, even under extreme weather conditions. Future work should focus on refining input data and optimizing the model by analyzing cases of extreme weather.