The emergence of rice panicle substantially changes the spectral reflectance of rice canopy and, as a result, decreases the accuracy of leaf area index (LAI) that was derived from vegetation indices (VIs). From a four-year field experiment with using rice varieties, nitrogen (N) rates, and planting densities, the spectral reflectance characteristics of panicles and the changes in canopy reflectance after panicle removal were investigated. A rice “panicle line”—graphical relationship between red-edge and near-infrared bands was constructed by using the near-infrared and red-edge spectral reflectance of rice panicles. Subsequently, a panicle-adjusted renormalized difference vegetation index (PRDVI) that was based on the “panicle line” and the renormalized difference vegetation index (RDVI) was developed to reduce the effects of rice panicles and background. The results showed that the effects of rice panicles on canopy reflectance were concentrated in the visible region and the near-infrared region. The red band (670 nm) was the most affected by panicles, while the red-edge bands (720–740 nm) were less affected. In addition, a combination of near-infrared and red-edge bands was for the one that best predicted LAI, and the difference vegetation index (DI) (976, 733) performed the best, although it had relatively low estimation accuracy (R² = 0.60, RMSE = 1.41 m²/m²). From these findings, correcting the near-infrared band in the RDVI by the panicle adjustment factor (θ) developed the PRDVI, which was obtained while using the “panicle line”, and the less-affected red-edge band replaced the red band. Verification data from an unmanned aerial vehicle (UAV) showed that the PRDVI could minimize the panicle and background influence and was more sensitive to LAI (R² = 0.77; RMSE = 1.01 m²/m²) than other VIs during the post-heading stage. Moreover, of all the assessed VIs, the PRDVI yielded the highest R2 (0.71) over the entire growth period, with an RMSE of 1.31 (m²/m²). These results suggest that the PRDVI is an efficient and suitable LAI estimation index.

The timely and robust prediction of wheat yield is very significant for grain trade and food security. In this study, the yield prediction model was developed by coupling an ensemble model with multi-source data, including vegetation indices (VIs) and meteorological data. The results showed that green chlorophyll vegetation index (GCVI) is the optimal remote sensing (RS) variable for predicting wheat yield compared with other VIs. The accuracy of the adaptive boosting- long short-term memory (AdaBoost-LSTM) ensemble model was higher than the LSTM model. AdaBoost-LSTM coupled with optimal input data had the best performance. The AdaBoost-LSTM model had strong robustness for predicting wheat yield under different irrigation and extreme weather events in general. Additionally, the accuracy of AdaBoost-LSTM for rainfed counties was higher than that for irrigation counties in most years except extreme years. The yield prediction model developed with the characteristic variables of the window from February to April had higher accuracy and smaller data requirements, which was the best prediction window. Therefore, wheat yield can be accurately predicted by the AdaBoost-LSTM model one to two months of lead time before maturity in the HHHP. Overall, the AdaBoost-LSTM model can achieve accurate and robust yield prediction in large-scale regions.

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.

The rapid and accurate estimation of leaf area index (LAI) through remote sensing holds significant importance for precise crop management. However, the direct construction of a vegetation index model based on multi-spectral data lacks robustness and spatiotemporal expansibility, making its direct application in practical production challenging. This study aimed to establish a simple and effective method for LAI estimation to address the issue of poor accuracy and stability that is encountered by vegetation index models under varying conditions. Based on seven years of field plot trials with different varieties and nitrogen fertilizer treatments, the Kalman filter (KF) fusion method was employed to integrate the estimated outcomes of multiple vegetation index models, and the fusion process was investigated by comparing and analyzing the relationship between fixed and dynamic variances alongside the fusion accuracy of optimal combinations during different growth stages. A novel multi-model integration fusion method, KF-DGDV (Kalman Filtering with Different Growth Periods and Different Vegetation Index Models), which combines the growth characteristics and uncertainty of LAI, was designed for the precise monitoring of LAI across various growth phases of rice. The results indicated that the KF-DGDV technique exhibits a superior accuracy in estimating LAI compared with statistical data fusion and the conventional vegetation index model method. Specifically, during the tillering to booting stage, a high R² value of 0.76 was achieved, while at the heading to maturity stage, it reached 0.66. In contrast, within the framework of the traditional vegetation index model, the red-edge difference vegetation index (DVIREP) model demonstrated a superior performance, with an R² value of 0.65, during tillering to booting stage, and 0.50 during the heading to maturity stage, respectively. The multi-model integration method (MME) yielded an R² value of 0.67 for LAI estimation during the tillering to booting stage, and 0.53 during the heading to maturity stage. Consequently, KF-DGDV presented an effective and stable real-time quantitative estimation method for LAI in rice.