The ability of process-based biogeochemical models in estimating the gross primary productivity (GPP) of alpine vegetation is largely hampered by the poor representation of phenology and insufficient calibration of model parameters. The development of remote sensing technology and the eddy covariance (EC) technique has made it possible to overcome this dilemma. In this study, we have incorporated remotely sensed phenology into the Biome-BGC model and calibrated its parameters to improve the modeling of GPP of alpine grasslands on the Tibetan Plateau (TP). Specifically, we first used the remotely sensed phenology to modify the original meteorological-based phenology module in the Biome-BGC to better prescribe the phenological states within the model. Then, based on the GPP derived from EC measurements, we combined the global sensitivity analysis method and the simulated annealing optimization algorithm to effectively calibrate the ecophysiological parameters of the Biome-BGC model. Finally, we simulated the GPP of alpine grasslands on the TP from 1982 to 2015 based on the Biome-BGC model after a phenology module modification and parameter calibration. The results indicate that the improved Biome-BGC model effectively overcomes the limitations of the original Biome-BGC model and is able to reproduce the seasonal dynamics and magnitude of GPP in alpine grasslands. Meanwhile, the simulated results also reveal that the GPP of alpine grasslands on the TP has increased significantly from 1982 to 2015 and shows a large spatial heterogeneity, with a mean of 289.8 gC/m²/yr or 305.8 TgC/yr. Our study demonstrates that the incorporation of remotely sensed phenology into the Biome-BGC model and the use of EC measurements to calibrate model parameters can effectively overcome the limitations of its application in alpine grassland ecosystems, which is important for detecting trends in vegetation productivity. This approach could also be upscaled to regional and global scales.

Automatic detection of buildings from very high resolution (VHR) satellite images is a current research hotspot in remote sensing and computer vision. However, many irrelevant objects with similar spectral characteristics to buildings will cause a large amount of interference to the detection of buildings, thus making the accurate detection of buildings still a challenging task, especially for images captured in complex environments. Therefore, it is crucial to develop a method that can effectively eliminate these interferences and accurately detect buildings from complex image scenes. To this end, a new building detection method based on the morphological building index (MBI) is proposed in this study. First, the local feature points are detected from the VHR remote sensing imagery and they are optimized by the saliency index proposed in this study. Second, a voting matrix is calculated based on these optimized local feature points to extract built-up areas. Finally, buildings are detected from the extracted built-up areas using the MBI algorithm. Experiments confirm that our proposed method can effectively and accurately detect buildings in VHR remote sensing images captured in complex environments.

Turbidity, relating to underwater light attenuation, is an important optical parameter for water quality evaluation. Satellite estimation of turbidity in alpine rivers is challenging for common ocean color retrieval models due to the differences in optical properties of the water bodies. In this study, we present a simple two-band semi-analytical turbidity (2BSAT) retrieval model for estimating turbidity in five alpine rivers with varying turbidity from 1.01 to 284 NTU. The model was calibrated and validated, respectively, while using one calibration dataset that was obtained from the Three Parallel Rivers basin and two independent validation datasets that were obtained from the Kaidu River basin and the Yarlung Zangbo River basin. The results show that the model has excellent performance in deriving turbidity in alpine rivers. We verified the consistency of the simulated reflectance and satellite-based reflectance and calibrated the 2BSAT model for the specified bands of high spatial resolution satellites in order to achieve the goal of remote sensing monitoring. It is concluded that the model can be used for the quantitative monitoring of turbidity in alpine rivers using satellite images. Based on the model, we used the Sentinel-2 images from one year to identify the seasonal patterns of turbidity of five alpine rivers and the Landsat series images from 1989 to 2018 to analyze the turbidity variation trends of these rivers. The results indicate that the turbidity of these alpine rivers usually presents the highest level in summer, followed by spring and autumn, and the lowest in winter. Meanwhile, the variation trends of turbidity over the past 30 years present distinctly different characteristics in the five rivers.

Vegetation restoration in the Loess Plateau (LP) of China is driven by atmospheric environmental changes (climate change, rising CO₂, and nitrogen deposition), land cover change (LCC) from ecological restoration projects (ERPs), and change in forest age. However, the dominant factors influencing vegetation restoration remain controversial. This study improved the Deep Crossing network by integrating bidirectional long short-term memory (Bi-LSTM) with embedding, creating the Deep Crossing LSTM Age (DC-LSTM-Age) network. It incorporates land cover type, forest age, and atmospheric environmental factors to reconstruct the leaf area index (LAI). We investigated the LAI increase (greening) driven by various factors and their dynamics in the Grain for Green Project (GGP) regions of the LP from 2001 to 2021. Results showed that DC-LSTM-Age network effectively simulated LAI values and its temporal dynamics in LCC regions, with superior validation performance (R ² = 0.87) compared to the Deep Crossing LSTM network (R ² = 0.84) that excluded forest age and the Bi-LSTM network (R ² = 0.79) that excluded forest age and land cover type. The greening trend in afforested regions (GGP-Forest, 0.013 m² m⁻²yr⁻¹) was much larger than in grass revegetation regions (GGP-Grass, 0.005 m² m⁻²yr⁻¹). Dominant drivers varied by restoration strategy: in GGP-Forest, LCC was the primary driver (0.25 m² m⁻², 52.9%), with an increasing impact over time. In GGP-Grass, atmospheric environmental changes dominated (0.127 m² m⁻², 78.5%), led by climate change (0.064 m² m⁻², 39.4%), CO₂ rising (0.056 m² m⁻², 35%), and nitrogen deposition change (0.007 m² m⁻², 4.1%). The CO₂ fertilization effect showed signs of saturation. This research highlights the crucial role of ERPs in LAI increase.

Chlorophyll-a(chl-a) has been used as an important indicator of water quality. Great efforts have been invested to develop remote-sensing-based chl-a retrieval models. However, due to the spatial difference in chl-a concentration, a single model usually cannot accurately predict the whole range of chl-a concentration. To test the performance of precedent chl-a models, we carried out an experiment along the upper and middle reaches of the Kaidu River and around some small ponds in the Bayanbulak Wetland. We measured water surface reflectance in the field and analyzed the chl-a concentration in the laboratory. Initially, we performed a sensitivity analysis of the spectrum band to chl-a concentration with the aim of identifying the most suitable bands for various chl-a models. We found that the water samples could be divided into two groups with a threshold of 4.50 mg/m³. Then, we tested the performance of 11 precedent chl-a retrieval models and 7 spectral index-based regression models from this study for all the sample datasets and the two separate datasets with relatively high and low chl-a concentrations. Through a complete comparison of the performance of these models, we selected the D3B model for water bodies with high chl-a concentration and OC2 model (ocean color 2) for low chl-a concentration waters, resulting in the hierarchical and piecewise retrieval algorithm OC2-D3B. The chl-a concentration of 4.50 mg/m³ corresponded to the D3B value of −0.051; therefore, we used −0.051 as the threshold value of the OC2-D3B model. The result of the OC2-D3B model showed a better performance than the other algorithms. Finally, we mapped the spatial distribution and seasonal pattern of chl-a concentration in Bayanbulak Wetland using Sentinel-2 images from 2016 to 2019. The results indicated that the chl-a concentration in the riparian ponds was generally in the range of 8–10 mg/m³, which was higher than that in rivers with a range of 2–4 mg/m³. The highest chl-a concentration usually appears in summer, followed by spring and autumn, and the lowest in winter. The correlation between meteorological data and chl-a concentration showed that temperature is the dominant factor for chl-a concentration changes. Our analytical framework could provide a better way to accurately map the spatial distribution of chl-a concentration in complex river systems.

Gross primary productivity (GPP) is an important indicator in research on carbon cycling in terrestrial ecosystems. High-accuracy GPP prediction is crucial for ecosystem health and climate change assessments. We developed a site-level GPP prediction method based on the GeoMAN model, which was able to extract spatiotemporal features and fuse external environmental factors to predict GPP on the Tibetan Plateau. We evaluated four models’ behavior—Random Forest (RF), Support Vector Machine (SVM), Deep Belief Network (DBN), and GeoMAN—in predicting GPP at nine flux observation sites on the Tibetan Plateau. The GeoMAN model achieved the best results (R² = 0.870, RMSE = 0.788 g Cm⁻² d⁻¹, MAE = 0.440 g Cm⁻² d⁻¹). Distance and vegetation type of the flux sites influenced GPP prediction, with the latter being more significant. The different grassland vegetation types exhibited different sensitivity to environmental factors (Ta, PAR, EVI, NDVI, and LSWI) for GPP prediction. Among them, the site located in the alpine swamp meadow was insensitive to changes in environmental factors; the GPP prediction accuracy of the site located in the alpine meadow steppe decreased significantly with the changes in environmental factors; and the GPP prediction accuracy of the site located in the alpine Kobresia meadow also varied with environmental factor changes, but to a lesser extent than the former. This study provides a good reference that deep learning model is able to achieve good accuracy in GPP simulation when considers spatial, temporal, and environmental factors, and the judgement made by deep learning model conforms to basic knowledge in the relevant field.