Maize (Zea mays L.) is a key global cereal crop with significant relevance to food security. Maize yield prediction is challenged by cultivar diversity and varying management practices. This preliminary study was conducted at Youyi Farm, Heilongjiang Province, China. Three maize cultivars (Songyu 438, Dika 1220, Dika 2188), two fertilization rates (700 and 800 kg·ha⁻¹), and three planting densities (70,000, 75,000, and 80,000 plants·ha⁻¹) were evaluated across 18 distinct cropping treatments. During the V6 (Vegetative 6-leaf stage), VT (Tasseling stage), R3 (Milk stage), and R6 (Physiological maturity) growth stages of maize, multi-temporal canopy spectral images were acquired using an unmanned aerial vehicle (UAV) equipped with a multispectral sensor. In situ measurements of key agronomic traits, including plant height (PH), stem diameter (SD), leaf area index (LAI), and relative chlorophyll content (SPAD), were conducted. The optimal vegetation indices (VIs) and agronomic traits were selected for developing a maize yield prediction model using the random forest (RF) algorithm. Results showed the following: (1) Vegetation indices derived from the red-edge band, particularly the normalized difference red-edge index (NDRE), exhibited a strong correlation with maize yield (R = 0.664), especially during the tasseling to milk ripening stage; (2) The integration of LAI and SPAD with NDRE improved model performance, achieving an R² of 0.69—an increase of 23.2% compared to models based solely on VIs; (3) Incorporating SPAD values from middle-canopy leaves during the milk ripening stage further enhanced prediction accuracy (R² = 0.74, RMSE = 0.88 t·ha⁻¹), highlighting the value of vertical-scale physiological parameters in yield modeling. This study not only furnishes critical technical support for the application of UAV-based remote sensing in precision agriculture at the field-plot scale, but also charts a clear direction for the synergistic optimization of multi-dimensional agronomic traits and spectral features.

To improve the physical consistency and interpretability of traditional drought indices, this study proposes a drought assessment model that couples physically based constraints with data-driven approaches, leading to the development of a Multivariate Drought Index (MDI). The model employs convolutional neural networks to achieve physically consistent downscaling, thereby obtaining a high-resolution Normalized Difference Water Index (NDWI), Temperature Vegetation Dryness Index (TVDI), Vegetation Condition Index (VCI), and Temperature Condition Index (TCI). Objective weights are determined using the Criteria Importance Through Intercriteria Correlation method, while random forest and Shapley Additive Explanations are integrated for nonlinear interpretation and physics-guided calibration, forming an ensemble framework that incorporates multi-source and multi-scale factors. Validation with multi-source data from 2000 to 2024 in the major maize-growing areas of Heilongjiang Province demonstrates that MDI outperforms single indices and the Vegetation Health Index (VHI), achieving a correlation coefficient (r = 0.87), coefficient of determination (R² = 0.87), RMSE (0.08), and classification accuracy (87.4%). During representative drought events, MDI identifies signals 16–20 days earlier than the Standardized Precipitation Evapotranspiration Index (SPEI) and the Soil Moisture Condition Index (SMCI), and effectively captures localized drought patches at a 250 m scale. Feature importance analysis indicates that the NDWI and TVDI are consistently identified as dominant factors across all three methods, aligning physically interpretable analysis with statistical contribution. Long-term risk zoning reveals that the central–western region of the study area constitutes a high-risk zone, accounting for 42.6% of the total. This study overcomes the limitations of single indices by integrating physical consistency with the advantages of data-driven methods, achieving refined spatiotemporal characterization and enhanced overall performance, while also demonstrating potential for application across different crops and regions.

In the field of smart agriculture, soil property data at the field scale drives the precision decision-making of agricultural inputs such as seeds and chemical fertilizers. However, soil texture has significant spatial variability at the field scale, and traditional remote sensing monitoring methods have certain data intermittency, which limits small-scale prediction research. In this study, based on the Google Earth Engine platform, soil synthetic images were generated according to different time intervals using mean compositing and median compositing modes, image bands were extracted, and spectral indices were introduced; combined with the random forest algorithm, the effects of different compositing time windows, compositing modes, and compositing data types on prediction accuracy were evaluated; and three partitioning strategies based on crop growth, soil synthetic image brightness, and soil type were adopted to conduct local partitioning regression of soil texture. The results show that: (1) The use of mean compositing of multi-year May images from 2021 to 2024 can improve prediction accuracy. When this method is combined with the “band reflectance + spectral indices” dataset, compared with other compositing methods, the R² of clay particles, silt particles, and sand particles can be increased by 8.89%, 9.50%, and 2.48% on average. (2) Compared with using only image band data, the introduction of spectral indices can significantly improve the prediction accuracy of soil texture at the field scale, and the R² of clay particles, silt particles, and sand particles is increased by 4.58%, 3.43%, and 4.59% on average, respectively. (3) Global regression is superior to local partitioning regression; however, the local partitioning regression strategy based on soil type has good accuracy performance. Under the optimal compositing method, the average R² of soil particles of each size fraction is only 1.08% lower than that of global regression, which has great application potential. This study innovatively constructs a comprehensive strategy of “moisture spectral indices + specific compositing time window + specific compositing mode + soil type partitioning”, providing a new paradigm for soil texture prediction at the field scale in Northeastern China, and lays the foundation for data-driven water and fertilizer decision-making.

Due to an oversight on behalf of the author, the affiliation of the first author was inadvertently omitted from the original publication