Accurate estimation of winter wheat yield is essential for ensuring food security. Recent studies on winter wheat yield estimation based on deep learning methods rarely explore the interpretability of the model from the perspective of crop growth mechanism. In this study, a multiscale winter wheat yield estimation framework (called MultiScaleWheatNet model) was proposed, which was based on time series remote sensing data and further takes into account meteorological and soil factors that affect wheat growth. The model integrated multimodal data from different temporal and spatial scales, extracting growth characteristics specific to particular growth stage based on the growth pattern of wheat phenological phase. It focuses on enhancing model accuracy and interpretability from the perspective of crop growth mechanisms. The results showed that, compared to mainstream deep learning architectures, the MultiScaleWheatNet model had good estimation accuracy in both rain-fed and irrigated farmlands, with higher accuracy in rain-fed farmlands (R² = 0.86, RMSE = 0.15 t·ha⁻¹). At the county scale, the accuracy of the model in estimating winter wheat yield was stable across three years (from 2021 to 2023, R² ≥ 0.35, RMSE ≤ 0.73 t·ha⁻¹, nRMSE ≤ 20.4%). Model interpretability results showed that, taking all growth stages together, the remotely sensed indices had relatively high contribution to wheat yield, with roughly equal contributions from meteorological and soil variables. From the perspective of the growth stages, the contribution of LAI in remote sensing factors demonstrated greater stability throughout the growth stages, particularly during the jointing, heading-filling and milky maturity stage; the combined impact of meteorological factors exhibited a discernible temporal sequence, initially dominated by water availability and subsequently transitioning to temperature and sunlight in the middle and late stages; soil factors demonstrated a close correlation with soil pH and cation exchange capacity in the early and late stages, and with organic carbon content in the middle stage. By deeply combining remote sensing, meteorological and soil data, the framework not only achieves high accuracy in winter wheat yield estimation, but also effectively interprets the dynamic influence mechanism of remote sensing data on yield from the perspective of crop growth, providing a scientific basis for precise field water and fertiliser management and agricultural decision-making.

In the current context of carbon neutrality, afforestation is an effective means of absorbing carbon dioxide. Stock can be used not only as an economic value index of forest wood resources but also as an important index of biomass and carbon storage estimation in forest emission reduction project evaluation. In this paper, we propose a data-driven machine learning framework and method for predicting plantation stock based on airborne LiDAR + satellite remote sensing, and carried out experimental verification at the site of the National Forest emission reduction project in Southern China. We used step-up regression and random forest (RF) to screen LiDAR and Landsat 8 OLI multispectral indicators suitable for the prediction of plantation stock, and constructed a plantation stock model based on machine learning (support vector machine regression, RF regression). Our method is compared with traditional statistical methods (stepwise regression and partial least squares regression). Through the verification of 57 plantation field survey data, the accuracy of the stand estimation model constructed using the RF method is generally better (ΔR² = 0.01~0.27, ΔRMSE = 1.88~13.77 m³·hm⁻², ΔMAE = 1.17~13.57 m³·hm⁻²). The model evaluation accuracy based on machine learning is higher than that of the traditional statistical method, and the fitting R² is greater than 0.91, while the fitting R² of the traditional statistical method is 0.85. The best fitting models were all support vector regression models. The combination of UAV point clouds and satellite multi-spectral images has the best modeling effect, followed by LiDAR point clouds and Landsat 8. At present, this method is only applicable to artificial forests; further verification is needed for natural forests. In the future, the density and quality of higher clouds could be increased. The validity and accuracy of the method were further verified. This paper provides a method for predicting the accumulation of typical Chinese plantations at the forest farm scale based on the “airborne LiDAR + satellite remote sensing” data-driven machine learning modeling, which has potential application value for the current carbon neutrality goal of the southern plantation forest emission reduction project.

Automated livestock monitoring in wide-area grasslands is a critical component of smart agriculture development. Devices such as Unmanned Aerial Vehicles (UAVs), remote sensing, and high-mounted cameras provide unique monitoring perspectives for this purpose. The high-resolution images they capture cover vast grassland backgrounds, where targets often appear as small, distant objects and are extremely unevenly distributed. Applying standard detectors directly to such images yields poor results and extremely high miss rates. To improve the detection accuracy of small targets in high-resolution images, methods represented by Slicing Aided Hyper Inference (SAHI) have been widely adopted. However, in specific scenarios, SAHI’s drawbacks are dramatically amplified. Its strategy of uniform global slicing divides each original image into a fixed number of sub-images, many of which may be pure background (negative samples) containing no targets. This results in a significant waste of computational resources and a precipitous drop in inference speed, falling far short of practical application requirements. To resolve this conflict between accuracy and efficiency, this paper proposes an efficient detection framework named CAMS-AI (Clustering and Adaptive Multi-level Slicing for Aided Inference). CAMS-AI adopts a “coarse-to-fine” intelligent focusing strategy: First, a Region Proposal Network (RPN) is used to rapidly locate all potential target areas. Next, a clustering algorithm is employed to generate precise Regions of Interest (ROIs), effectively focusing computational resources on target-dense areas. Finally, an innovative multi-level slicing strategy and a high-precision model are applied only to these high-quality ROIs for fine-grained detection. Experimental results demonstrate that the CAMS-AI framework achieves a mean Average Precision (mAP) comparable to SAHI while significantly increasing inference speed. Taking the RT-DETR detector as an example, while achieving 96% of the mAP_50–95 accuracy level of the SAHI method, CAMS-AI’s end-to-end frames per second (FPS) is 10.3 times that of SAHI, showcasing its immense application potential in real-world, high-resolution monitoring scenarios.