The prediction of crop yield plays a crucial role in national economic development, encompassing grain storage, processing, and grain price trends. Employing multiple sensors to acquire remote sensing data and utilizing machine learning algorithms can enable accurate, fast, and nondestructive yield prediction for maize crops. However, current research heavily relies on single-type remote sensing data and traditional machine learning methods, resulting in the limited robustness of yield prediction models. To address these limitations, this study introduces a field-scale maize yield prediction model named the convolutional neural network–attention–long short-term memory network (CNN-attention-LSTM) model, which utilizes multimodal remote sensing data collected by multispectral and light detection and ranging (LIDAR) sensors mounted on unmanned aerial vehicles (UAVs). The model incorporates meteorological data throughout the crop reproductive stages and employs the normalized difference vegetation index (NDVI), normalized difference red edge (NDRE), soil-adjusted vegetation index (SAVI), and enhanced vegetation index (EVI) for the initial part of the vegetative stage (initial part of the V period), the later part of the vegetative stage (later part of the V period), the reproductive stage (R period), and the maturity stage (M period), along with LIDAR data for Point_75–100 in the later part of the V period, Point_80–100 in the R period, and Point_50–100 in the M period, complemented by corresponding meteorological data as inputs. The resulting yield estimation demonstrates exceptional performance, with an R² value of 0.78 and an rRMSE of 8.27%. These results surpass previous research and validate the effectiveness of multimodal data in enhancing yield prediction models. Furthermore, to assess the superiority of the proposed model, four machine learning algorithms—multiple linear regression (MLR), random forest regression (RF), support vector machine (SVM), and backpropagation (BP)—are compared to the CNN-attention-LSTM model through experimental analysis. The outcomes indicate that all alternative models exhibit inferior prediction accuracy compared to the CNN-attention-LSTM model. Across the test dataset within the study area, the R² values for various nitrogen fertilizer levels consistently exceed 0.75, illustrating the robustness of the proposed model. This study introduces a novel approach for assessing maize crop yield and provides valuable insights for estimating the yield of other crops. Full article

Multitemporal crop classification approaches have demonstrated high performance within a given season. However, cross-season and cross-region crop classification presents a unique transferability challenge. This study addresses this challenge by adopting a domain generalization approach, e.g., by training models on multiple seasons to improve generalization to new, unseen target years. We utilize a comprehensive five-year Sentinel-2 dataset over different agricultural regions in Slovakia and a diverse crop scheme (eight crop classes). We evaluate the performance of different machine learning classification algorithms, including random forests, support vector machines, quadratic discriminant analysis, and neural networks. Our main findings reveal that the transferability of models across years differs between regions, with the Danubian lowlands demonstrating better performance (overall accuracies ranging from 91.5% in 2022 to 94.3% in 2020) compared to eastern Slovakia (overall accuracies ranging from 85% in 2022 to 91.9% in 2020). Quadratic discriminant analysis, support vector machines, and neural networks consistently demonstrated high performance across diverse transferability scenarios. The random forest algorithm was less reliable in generalizing across different scenarios, particularly when there was a significant deviation in the distribution of unseen domains. This finding underscores the importance of employing a multi-classifier analysis. Rapeseed, grasslands, and sugar beet consistently show stable transferability across seasons. We observe that all periods play a crucial role in the classification process, with July being the most important and August the least important. Acceptable performance can be achieved as early as June, with only slight improvements towards the end of the season. Finally, employing a multi-classifier approach allows for parcel-level confidence determination, enhancing the reliability of crop distribution maps by assuming higher confidence when multiple classifiers yield similar results. To enhance spatiotemporal generalization, our study proposes a two-step approach: (1) determine the optimal spatial domain to accurately represent crop type distribution; and (2) apply interannual training to capture variability across years. This approach helps account for various factors, such as different crop rotation practices, diverse observational quality, and local climate-driven patterns, leading to more accurate and reliable crop classification models for nationwide agricultural monitoring. Full article

In order to address the challenge of early detection of cotton verticillium wilt disease, naturally infected cotton plants in the field, which were divided into five categories based on the degree of disease severity, have been investigated in this study. Canopies of infected cotton plants were analyzed with spectral data measured, and various preprocessing techniques, including multiplicative scatter correction (MSC) and MSC-continuous wavelet analysis algorithms, were used to predict the disease severity. With a combination of support vector machine (SVM) models with such optimization algorithms as genetic algorithm (GA), grid search (GS), particle swarm optimization (PSO), and grey wolf optimizer (GWO), a grading model of cotton verticillium wilt disease was established in this study. The study results show that the MSC-PSO-SVM model outperforms the other three models in terms of classification accuracy, and the accuracy, macro precision, macro recall, and macro F1-score of this model are 80%, 81.26%, 80%, and 79.57%, respectively. Among those eight models constructed on the basis of continuous wavelet analyses using mexh and db3, the MSC-db3(2³)-PSO-SVM and MSC-db3(2³)-GWO-SVM models perform best, with the latter having a shorter running time. An overall evaluation shows that the MSC-db3(2³)-GWO-SVM model is an optimal model, with values of its accuracy, macro precision, macro recall, and macro F1-score indicators being 91.2%, 92.02%, 91.2%, and 91.16%, respectively. Moreover, under this model, the prediction accuracy on disease levels 1 and 5 has achieved the highest rate of 100%, with a prediction accuracy rate of 88% on disease level 2 and the lowest prediction accuracy rate of 84% on both disease levels 3 and 4. These results demonstrate that it is effective to use spectral technology in classifying the cotton verticillium wilt disease and satisfying the needs of field detection and grading. This study provides a new approach for the detection and grading of cotton verticillium wilt disease and offered a theoretical basis for early prevention, precise drug application, and instrument development for the disease. Full article

The crop drought risk assessment is an important basis for mitigating the effects of drought on crops. The study of drought using crop growth models is an integral part of agricultural drought risk research. The current Decision Support System for Agrotechnology Transfer (DSSAT) model is not sufficiently sensitive to moisture parameters when performing simulations, and most studies that conduct different scenario simulations to assess crop drought vulnerability are based on the site-scale. In this paper, we improved the moisture sensitivity of the Crop Environment Resource Synthesis System (CERES)-Wheat to improve the simulation accuracy of winter wheat under water stress, and then we assessed the drought intensity in the Beijing-Tianjin-Hebei region and constructed a gridded vulnerability curve. The grid vulnerability curves (1 km × 1 km) were quantitatively characterized using key points, and the drought risk distribution and zoning of winter wheat were evaluated under different return periods. The results show that the stress mechanism of coupled water and photosynthetic behavior improved the CERES-Wheat model. The accuracy of the modified model improved in terms of the above-ground biomass and yield compared with that before the modification, with increases of 20.39% and 11.45% in accuracy, respectively. The drought hazard intensity index of winter wheat in the study area from 1970 to 2019 exhibited a trend of high in the southwest and low in the southeast. The range of the multi-year average drought hazard intensity across the region was 0.29–0.61. There were some differences in the shape and characteristic covariates of the drought vulnerability curves among the different sub-zones. In terms of the cumulative loss rates, almost the entire region had a cumulative drought loss rate of 49.00–54.00%. Overall, the drought risk index decreased from west to east and from north to south under different return periods. This quantitative evaluation of the drought hazard intensity index provides a reference for agricultural drought risk evaluation. Full article

In July 2021, a flooding event, which attracted the attention of the whole country and even the world, broke out in Henan, resulting in dramatic losses across multiple fields (e.g., economic and agricultural). The basin at the junction of Hebi, Xinxiang, and Anyang was the most affected region, as the spread of water from the Wei river submerged surrounding agricultural land (e.g., corn-dominated). To comprehensively evaluate the flooding impacts, we proposed a framework to detect the flooding area and evaluated the degree of loss using satellite time series data. First, we proposed a double-Gaussian model to adaptively determine the threshold for flooding extraction using Synthetic Aperture Radar (SAR) data. Then, we evaluated the disaster levels of flooding with field survey samples and optical satellite images. Finally, given that crops vary in their resilience to flooding, we measured the vegetation index change before and after the flooding event using satellite time series data. We found the proposed double-Gaussian model could accurately extract the flooding area, showing great potential to support in-time flooding evaluation. We also showed that the multispectral satellite images could potentially support the classification of disaster levels (i.e., normal, slight, moderate, and severe), with an overall accuracy of 88%. Although these crops were temporarily affected by this flooding event, most recovered soon, especially for the slightly and moderately affected regions. Overall, the distribution of resilience of these affected crops was basically in line with the results of classified disaster levels. The proposed framework provides a comprehensive aspect to the retrospective study of the flooding process on crops with diverse disaster levels and resilience. It can provide rapid and timely flood damage assessment and support emergency management and disaster verification work. Full article

Corn (Zea mays L.) nitrogen (N) management requires monitoring plant N concentration (Nc) with remote sensing tools to improve N use, increasing both profitability and sustainability. This work aims to predict the corn Nc during the growing cycle from Sentinel-2 and Sentinel-1 (C-SAR) sensor data fusion. Eleven experiments using five fertilizer N rates (0, 60, 120, 180, and 240 kg N ha⁻¹) were conducted in the Pampas region of Argentina. Plant samples were collected at four stages of vegetative and reproductive periods. Vegetation indices were calculated with new combinations of spectral bands, C-SAR backscatters, and sensor data fusion derived from Sentinel-1 and Sentinel-2. Predictive models of Nc with the best fit (R² = 0.91) were calibrated with spectral band combinations and sensor data fusion in six experiments. During validation of the models in five experiments, sensor data fusion predicted corn Nc with lower error (MAPE: 14%, RMSE: 0.31 %Nc) than spectral band combination (MAPE: 20%, RMSE: 0.44 %Nc). The red-edge (704, 740, 740 nm), short-wave infrared (1375 nm) bands, and VV backscatter were all necessary to monitor corn Nc. Thus, satellite remote sensing via sensor data fusion is a critical data source for predicting changes in plant N status. Full article

Sun-induced chlorophyll fluorescence (SIF) has shown potential in quantifying plant responses to environmental changes by which abiotic drivers are dominated. However, SIF is a mixed signal influenced by factors such as leaf physiology, canopy structure, and sun-sensor geometry. Whether the physiological information contained in SIF can better quantify crop disease stresses dominated by biological drivers, and clearly explain the physiological variability of stressed crops, has not yet been sufficiently explored. On this basis, we took winter wheat naturally infected with stripe rust as the research object and conducted a study on the responses of physiological signals and reflectivity spectrum signals to crop disease stress dominated by biological drivers, based on in situ canopy-scale and leaf-scale data. Physiological signals include SIF, SIF_yield (normalized by absorbed photosynthetically active radiation), fluorescence yield (Φ_F) retrieved by NIRvP (non-physiological components of canopy SIF) and relative fluorescence yield (Φ_F-r) retrieved by near-infrared radiance of vegetation (NIRvR). Reflectance spectrum signals include normalized difference vegetation index (NDVI) and near-infrared reflectance of vegetation (NIRv). At the canopy scale, six signals reached extremely significant correlations (P < 0.001) with disease severity levels (SL) under comprehensive experimental conditions (SL without dividing the experimental samples) and light disease conditions (SL < 20%). The strongest correlation between NDVI and SL (R = 0.69) was observed under the comprehensive experimental conditions, followed by NIRv (R = 0.56), Φ_F-r (R = 0.53) and SIF (R = 0.51), and the response of Φ_F (R = 0.45) and SIF_yield (R = 0.34) to SL was weak. Under lightly diseased conditions, Φ_F-r (R = 0.62) showed the strongest response to disease, followed by SIF_yield (R = 0.60), SIF (R = 0.56) and NIRv (R = 0.54). The weakest correlation was observed between Φ_F and SL (R = 0.51), which also showed a result approximating NDVI (R = 0.52). In the case of a high level of crop disease severity, NDVI showed advantages in disease monitoring. In the early stage of crop diseases, which we pay more attention to, compared with SIF and reflectivity spectrum signals, Φ_F-r estimated by the newly proposed ‘NIRvR approach’ (which uses SIF together with NIRvR (i.e., SIF/ NIRvR) as a substitute for Φ_F) showed superior ability to monitor crop physiological stress, and was more sensitive to plant physiological variation. At the leaf scale, the response of SIF to SL was stronger than that of NDVI. These results validate the potential of Φ_F-r estimated by the NIRvR approach to monitoring disease stress dominated by biological drivers, thus providing a new research avenue for quantifying crop responses to disease stress. Full article

The crop model data assimilation approach has been acknowledged as an effective tool for monitoring crop growth and estimating yield. However, the choice of assimilated variables and the mismatch in scale between remotely sensed observations and crop model-simulated state variables have various effects on the performance of yield estimation. This study aims to examine the accuracy of crop yield estimation through the joint assimilation of leaf area index (LAI) and soil moisture (SM) and to examine the scale effect between remotely sensed data and crop model simulations. To address these issues, we proposed an improved crop data-model assimilation (CDMA) framework, which integrates LAI and SM, as retrieved from remotely sensed data, into the World Food Studies (WOFOST) model using the ensemble Kalman filter (EnKF) approach for winter wheat yield estimation. The results showed that the yield estimation at a 10 m grid size outperformed that at a 500 m grid size, using the same assimilation strategy. Additionally, the winter wheat yield estimation accuracy was higher when using the bivariate data assimilation method (R² = 0.46, RMSE = 756 kg/ha) compared to the univariate method. In conclusion, our study highlights the advantages of joint assimilating LAI and SM for crop yield estimation and emphasizes the importance of finer spatial resolution in remotely sensed observations for crop yield estimation using the CDMA framework. The proposed approach would help to develop a high-accuracy crop yield monitoring system using optical and SAR retrieved parameters. Full article