The accurate and rapid estimation of the aboveground biomass (AGB) of rice is crucial to food security. Unmanned aerial vehicles (UAVs) mounted with hyperspectral sensors can obtain images of high spectral and spatial resolution in a quick and effective manner. Integrating UAV-based spatial and spectral information has substantial potential for improving crop AGB estimation. Hyperspectral remote-sensing data with more continuous reflectance information on ground objects provide more possibilities for band selection. The use of band selection for the spectral vegetation index (VI) has been discussed in many studies, but few studies have paid attention to the band selection of texture features in rice AGB estimation. In this study, UAV-based hyperspectral images of four rice varieties in five nitrogen treatments (N0, N1, N2, N3, and N4) were obtained. First, multiple spectral bands were used to identify the optimal bands of the spectral vegetation indices, as well as the texture features; next, the vegetation index model (VI model), the vegetation index combined with the corresponding-band textures model (VI+CBT model), and the vegetation index combined with the full-band textures model (VI+FBT model) were established to compare their respective rice AGB estimation abilities. The results showed that the optimal bands of the spectral and textural information for AGB monitoring were inconsistent. The red-edge and near-infrared bands demonstrated a strong correlation with the rice AGB in the spectral dimension, while the green and red bands exhibited a high correlation with the rice AGB in the spatial dimension. The ranking of the monitoring accuracies of the three models, from highest to lowest, was: the VI+FBT model, then the VI+CBT model, and then the VI model. Compared with the VI model, the R² of the VI+FBT model and the VI+CBT model increased by 1.319% and 9.763%, respectively. The RMSE decreased by 2.070% and 16.718%, respectively, while the rRMSE decreased by 2.166% and 16.606%, respectively. The results indicated that the integration of vegetation indices and textures can significantly improve the accuracy of rice AGB estimation. The full-band textures contained richer information that was highly related to rice AGB. The VI model at the tillering stage presented the greatest sensitivity to the integration of textures, and the models in the N3 treatment (1.5 times the normal nitrogen level) gave the best AGB estimation compared with the other nitrogen treatments. This research proposes a reliable modeling framework for monitoring rice AGB and provides scientific support for rice-field management.

Timely and accurate crop yield estimation is crucial for managing crops, trade, and food security. The combination of remote sensing technology with machine learning methods is increasingly popular for global yield prediction. However, traditional machine learning methods rely on data correlation rather than causality, leading to poor interpretability. To address this issue, we propose a novel approach that combines structural causal model (SCM) with deep learning to develop a causal graph attention network model (SCM-GAT) based on causal relationships for soybean yield prediction at the county level of 10 major soybean-producing states in the United States. The SCM-GAT model considers not only conventional vegetation indices and weather variables but also the causal relationships between variables as inputs. Using independent validation and five-fold cross-validation strategies, our results show that the predictive performance of the SCM-GAT model is not only superior to traditional prediction models, such as selection operator regression (LASSO), random forest (RF), but also superior to the common deep learning models based on correlation relationships, such as long short-term memory network (LSTM), and transformer. It is also proved to be more robust than other models under extreme weather events. Additionally, we identify branching to blooming and blooming to setting pods as the key growth phases for soybean yield, and adding these phases as inputs to the model further improves prediction accuracy. Our findings suggest that incorporating causal relationships in deep learning models can improve prediction accuracy. This study provides a novel approach for remote sensing prediction of crop yield.

The phenology indicator of vegetation green-up dates (GUD) is prone to being affected by changes in temperature. However, the influencing degree of urbanization-induced temperature warming on vegetation GUDs among different vegetation species along the urban-rural gradient remains inadequately described. In this study, based on the long-term (2001–2019) satellite-derived vegetation GUDs and nighttime land surface temperature (LST) of forests, grasslands, and croplands along the urban-rural gradient with Beijing (China) as a case study area, the responses of vegetation GUDs to temperature changes were quantitatively analyzed, taking into account the vegetation types and distances away from the urban domain. The results show that (1) long-term GUDs and LST are significantly negatively correlated, characterized by a weaker significant correlation near the urban area when compared with its surrounding areas, with the greatest absolute linear correlation coefficients (r) happening at rings 32 km (r_max = −0.93, forests), 20 km and 48 km (r_max = −0.83, grasslands), and 34 km (r_max = −0.82, croplands), respectively; (2) the magnitude of change in GUDs over the past 19 year (2001–2019) are significantly positively correlated with these in LST near the urban area, demonstrating a distance-decay trend, with the greatest advance in GUDs occurring at the ring nearest the urban area, by about 20 days (forests), 24.5 days (grasslands), and 15.6 days (croplands), respectively; (3) the spatial pattern of the response rate of GUDs change to LST change (days K⁻¹) also showed a declining trend with distance, with GUD advanced by 6.8 days K⁻¹ (forests), 7.5 days K⁻¹ (grasslands), and 4.9 days K⁻¹ (croplands) at the closest ring to the urban, decreasing to about 2.3 days K⁻¹ (48 km), 4.1 days K⁻¹ (18 km), and 1 day K⁻¹ (18 km), respectively, indicating a notable influence of temperature warming on vegetation GUDs near the urban domains.