Optimizing Crop Maximum Carboxylation Rate Using Machine Learning to Improve Maize Yield Estimation Under Drought Conditions

Abstract

Accurate yield estimation is crucial for ensuring national food security and balancing supply and demand. Remote sensing (RS) process models are commonly used for regional-scale crop yield estimation, with the maximum carboxylation rate at 25° C (Vm25) being a key parameter influenced by genetic varieties, environmental conditions, and spatio-temporal variations. However, most remote sensing process models use a fixed Vm25value to simulate maize yield at regional scales. These models ignore variations in Vm25across time, space, and environmental conditions, leading to uncertainties in simulation. To address this issue, we developed a convolutional neural network (CNN) model combined with Vm25-related variables to estimate dynamic Vm25values for maize in Ningxia (NX), a typical semi-arid region of China. By integrating the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), and Leaf Area Index (LAI) with three drought-related hydrometeorological factors—Evapotranspiration (ET), Vapor Pressure Deficit (VPD), and Soil Water Content (SWC)—the model's prediction accuracy of Vm25was significantly improved, achieving an R2of 0.88 and an RMSE of 2.21 μmol m-2s-1on the test set. These dynamic Vm25values were then integrated into the RS process model (PRYM-Maize-Dr) to improve maize yield simulations under drought conditions in NX. Validation using data from 2010 to 2021 showed that, at the city level, the R2increased from 0.67 to 0.78 and RMSE decreased from 0.57 t ha-1to 0.43 t ha-1, while at the county level, the R2increased from 0.59 to 0.71 and RMSE decreased from 0.60 t ha-1to 0.53 t ha-1. These results highlight the potential of integrating RS process models with optimized Vm25for accurate spatio-temporal crop yield estimation at the regional scale.

Plant phenotyping relevance

CNNとリモートセンシング変数により、トウモロコシの生理形質Vm25を動的推定する手法を開発・検証しており、単なる収量測定ではなく植物形質の取得・抽出が中心である。

Code and data availability

公開本文の所在を確認できませんでした。非公開または購読が必要な可能性があります。

No evidence-backed public reproduction asset is currently recorded.