The concentrations of carbon, nitrogen, and phosphorus in water bodies significantly influence aquatic ecological conditions. By collecting multitemporal hyperspectral data and water quality parameter data from water bodies and through systematic preprocessing of hyperspectral data combined with multimethod sensitive band selection, an optimal spectral feature subset was determined. Within a machine learning framework, multiple combined remote sensing inversion models were constructed to identify the optimal inversion model for each water quality parameter, along with corresponding preprocessing methods and sensitive bands. The results indicate that differential processing of remote sensing reflectance enhances model accuracy. Sensitive band selection effectively eliminates redundant bands, significantly improving the computational efficiency of inversion models. XGBoost demonstrated superior accuracy in constructing 240 water quality parameter inversion models because of its unique algorithmic design. However, model accuracy is not solely determined by algorithmic complexity or predictive capability but rather by the combined effect of algorithm performance and input feature quality. Verification of the inversion model’s generalization ability via an independent dataset demonstrated its capacity for generalization. These findings provide valuable insights for the reliable application of hyperspectral data in aquatic environmental remote sensing and offer support for regional water quality conservation efforts.

Chlorophyll a (Chla), total phosphorus (TP), total nitrogen (TN), and turbidity (Turb) are key indicators for assessing water eutrophication. To overcome the limitations of conventional regression methods, this study developed and compared inversion models for these parameters using Landsat-8 OLI imagery and field data, comparing multiple linear regression and seven machine learning algorithms: Genetic Algorithm- and Particle Swarm-optimized Backpropagation Neural Networks (BPNNs), Convolutional Neural Network (CNN), Extreme Learning Machine (ELM), Random Forest (RF), XGBoost, and Support Vector Regression (SVR). The results revealed that traditional regression performed better for optically active parameters (Chla and Turb) than for non-optically active ones (TP and TN), whereas machine learning models significantly improved accuracy, particularly for TP and TN. The XGBoost model achieved the highest performance (R² > 0.90 for all parameters). Post-calibration analysis further delineated the spatial distributions and inter-parameter correlations in Pingzhai Reservoir, providing a robust method for water quality monitoring and assessment.

Investigating land cover patterns, changes in carbon stocks, and forecasting future conditions are essential for formulating regional sustainable development strategies and enhancing ecological and environmental quality. This study centers on Guiyang, a mountainous urban area in southwestern China, to analyze the dynamic changes in land cover and their effects on carbon stocks from 2000 to 2035. A carbon stocks assessment framework was developed using a cellular automaton-based artificial neural network model (CA-ANN), the InVEST model, and the geographical detector model to predict future land cover changes and identify the primary drivers of variations in carbon stocks. The results indicate that (1) from 2000 to 2020, impervious surfaces expanded significantly, increasing by 199.73 km². Compared to 2020, impervious surfaces are projected to increase by 1.06 km², 13.54 km², and 34.97 km² in 2025, 2030, and 2035, respectively, leading to further reductions in grassland and forest areas. (2) Over time, carbon stocks in Guiyang exhibited a general decreasing trend; spatially, carbon stocks were higher in the western and northern regions and lower in the central and southern regions. (3) The level of greenness, measured by the normalized vegetation index (NDVI), significantly influenced the spatial variation of carbon stocks in Guiyang. Changes in carbon stocks resulted from the combined effects of multiple factors, with the annual average temperature and NDVI being the most influential. These findings provide a scientific basis for advancing low-carbon development and constructing an ecological civilization in Guiyang.

Accurate monitoring of water quality in karst mountainous reservoirs, where the ecosystems are fragile, is central to sustainable water resource management and risk mitigation. Existing remote sensing inversion studies, however, have mostly relied on spectral reflectance alone, overlooking the synergistic effects of meteorological variables, while machine learning models remain too opaque for meaningful interpretation. Taking Pingzhai Reservoir as a case study, this study develops two machine learning inversion frameworks. The first is driven solely by Sentinel-2 multispectral imagery and compares Random Forest, LightGBM, XGBoost, and CatBoost. The second couples multispectral data with meteorological variables and, based on the optimal model, predicts dissolved oxygen (DO), ammonia nitrogen (NH₃-N), total nitrogen (TN), and pH. SHAP is subsequently used to quantify the contribution of each input and to analyze how different features influence model predictions. Multisource data fusion is found to improve inversion accuracy, and Random Forest yields the best performance among the four models, with R² values of 0.88, 0.68, 0.62, and 0.89 for DO, NH₃-N, TN, and pH, respectively. SHAP analysis revealed distinct dominant drivers for different water quality parameters. The framework produced good inversion results at Pingzhai Reservoir, offering an interpretable method for water quality monitoring in karst mountain reservoirs.