Current remote sensing-based aerosol optical depth (AOD) products have coarse spatial resolutions, which are useful for studies at continental and global scales, but unsatisfactory for local scale applications, such as urban air pollution monitoring. In this study, we investigated the possibility of using Landsat imagery to develop high-resolution AOD estimations at 30 m based on machine learning algorithms. We assessed the performance of six machine learning algorithms, including Extreme Gradient Boosting, Random Forest, Cascade Random Forest, Gradient Boosted Decision Trees, Extremely Randomized Trees, and Multiple Linear Regression. To obtain accurate AOD estimations, we used prior knowledge from multiple sources as inputs to the machine learning models, including the Global Land Surface Satellite (GLASS) albedo, the 1-km AOD product from MODIS data using the Multi-Angle Implementation of Atmospheric Correction (MAIAC) algorithm, and meteorological and surface elevation data. A total of 13,624 AOD measurements from Aerosol Robotic Network (AERONET) sites were used for model training and validation. We found that all six algorithms exhibited good performance, with R² values ranging from 0.73 to 0.78 and AOD root-mean-square errors (RMSE) ranging from 0.089 to 0.098. The extremely randomized trees algorithm, however, demonstrated marginally superior performance as compared to the other algorithms; hence, it was used to produce AOD estimates at a 30 m resolution for one Landsat scene coving Beijing in 2013–2019. Through a comparison with overlapping AERONET observations, a high level of accuracy was achieved, with an R² = 0.889 and an RMSE = 0.156. Our method can be potentially used to generate a global high-resolution AOD dataset based on Landsat imagery.

Soybeans are rich in high-quality protein and raw materials for producing hundreds of chemical products. Consequently, soybean cultivation has gained widespread prevalence across diverse geographic regions. Soybean breeding necessitates the development of early-, standard-, and late-maturing cultivars to accommodate cultivation at various latitudes, thereby optimizing the utilization of solar radiation. In the practical process of determining the maturity of soybean breeding materials within the breeding field, the ripeness is assessed based on three critical criteria: pod moisture content, leaf color, and the degree of leaf shedding. These parameters reflect the crown structure, physicochemical parameters, and reproductive organ changes in soybeans during the maturation process. Therefore, methods for analyzing soybean maturity at the breeding plot scale should match the standards of agricultural experts to the maximum possible extent. This study presents a hyperspectral remote sensing approach for monitoring soybean maturity. We collected five periods of unmanned aerial vehicle (UAV)-based soybean canopy hyperspectral digital orthophoto maps (DOMs) and ground-level measurements of leaf chlorophyll content (LCC), flavonoids (Flav), and the nitrogen balance index (NBI) from a breeding farm. This study explores the following aspects: (1) the correlations between soybean LCC, NBI, Flav, and maturity; (2) the estimation of soybean LCC, NBI, and Flav using Gaussian process regression (GPR), partial least squares regression (PLSR), and random forest (RF) regression techniques; and (3) the application of threshold-based methods in conjunction with normalized difference vegetation index (NDVI)+LCC and NDVI+NBI for soybean maturity monitoring. The results of this study indicate the following: (1) Soybean LCC, NBI, and Flav are associated with maturity. LCC increases during the beginning bloom period (P1) to the beginning seed period (P3) and sharply decreases during the beginning maturity period (P4) stage. Flav continues to increase from P1 to P4. NBI remains relatively consistent from P1 to P3 and then drops rapidly during the P4 stage. (2) The GPR, PLSR, and RF methodologies yield comparable accuracy in estimating soybean LCC (coefficient of determination (R²): 0.737–0.832, root mean square error (RMSE): 3.35–4.202 Dualex readings), Flav (R²: 0.321–0.461, RMSE: 0.13–0.145 Dualex readings), and NBI (R²: 0.758–0.797, RMSE: 2.922–3.229 Dualex readings). (3) The combination of the threshold method with NDVI < 0.55 and NBI < 8.2 achieves the highest classification accuracy (accuracy = 0.934). Further experiments should explore the relationships between crop NDVI, the Chlorophyll Index, LCC, Flav, and NBI and crop maturity for different crops and ecological areas.

The accurate monitoring of forest cover and its changes are essential for environmental change research, but current satellite products for forest coverage carry many uncertainties. This study used 30-m Landsat-8 data, and aggregated 1-m GaoFen-2 (GF-2) satellite images to construct the training samples and used multiple machine learning algorithms (MLAs) to estimate the fractional forest cover (FFC) in China’s Three North Region (TNR). In this study, multiple MLAs were merged to construct stacked generalization (SG) models based on the idea of SG, and the performances of the MLAs in the FFC estimation were evaluated. The results of the 10-fold cross-validation showed that all non-linear algorithms had a good performance, with an R² value of greater than 0.8 and a root-mean square error (RMSE) of less than 0.05. In the bagging ensemble, the random forest (RF) (R² = 0.993, RMSE = 0.020) model performed the best and in the boosting ensemble, the light gradient boosted machine (LGBM) (R² = 0.992, RMSE = 0.022) performed the best. Although the evaluation index of the RF is slightly better than that of the LGBM, the independent validation results show that the two models have similar performances. The model evaluation results of the independent datasets showed that, in the SG model, the performance of the SG(LGBM) (R² = 0.991, RMSE = 0.034) was better than that of the single or non-ensemble model. Comparing the FFC estimates of our model with those of existing datasets showed that our model exhibited more forest spatial distribution details and higher accuracy in complex landscapes. Overall, in this study, the method of using high-resolution remote sensing (RS) images to extract samples for FFC estimation is feasible. Our results demonstrate the potential of the ensemble MLAs to map the FFC. The research results also show that among many MALs, the RF algorithm is the most suitable algorithm for estimating FFC, which provides a reference for future research.