Cloud obscuration leaves significant gaps in MODIS snow cover products. In this study, an innovative gap-filling method based on the concept of non-local spatio-temporal filtering (NSTF) is proposed to reconstruct the cloud gaps in MODIS fractional snow cover (SCF) products. The ground information of a gap pixel was estimated by using the appropriate similar pixels in the remaining known part of an image via an automatic machine learning technique. We take the MODIS SCF product cloud gap filling data from 2001 to 2016 in Northern Xinjiang, China as an example. The results demonstrate that the methodology can generate almost continuous spatio-temporal, daily MODIS SCF images, and it leaves only 0.52% of cloud gaps long-term, on average. The validation results based on “cloud assumption” exhibit high accuracy, with a higher $R^2$ exceeding 0.8, a lower RMSE of 0.1, an overestimated error of 1.13%, an underestimated error of 1.4%, and a spatial efficiency (SPAEF) of 0.78. The validation based on 50 in situ snow depth observations demonstrates the superiority of the methodology in terms of accuracy and consistency. The overall accuracy is 93.72%. The average omission and commission error have increased approximately 1.16 and 0.53% compared with the original MODIS SCF products under a clear sky term.

Wildfires have a significant impact on the atmosphere, terrestrial ecosystems, and society. Real-time monitoring of wildfire locations is crucial in fighting wildfires and reducing human casualties and property damage. Geostationary satellites offer the advantage of high temporal resolution and are gradually being used for real-time fire detection. In this study, we constructed a fire label dataset using the stable VNP14IMG fire product and used the random forest (RF) model for fire detection based on Himawari-8 multiband data. The band calculation features related brightness temperature, spatial features, and auxiliary data as input used in this framework for model training. We also used a recursive feature elimination method to evaluate the impact of these features on model accuracy and to exclude redundant features. The daytime and nighttime RF models (RF-D/RF-N) are separately constructed to analyze their applicability. Finally, we extensively evaluated the model performance by comparing them with the Japan Aerospace Exploration Agency (JAXA) wildfire product. The RF models exhibited higher accuracy, with recall and precision rates of 95.62% and 59%, respectively, and the recall rate for small fires was 19.44% higher than that of the JAXA wildfire product. Adding band calculation features and spatial features, as well as feature selection, effectively reduced the overfitting and improved the model’s generalization ability. The RF-D model had higher fire detection accuracy than the RF-N model. Omission errors and commission errors were mainly concentrated in the adjacent pixels of the fire clusters. In conclusion, our VIIRS fire product and Himawari-8 data-based fire detection model can monitor the fire location in real time and has excellent detection capability for small fires, making it highly significant for fire detection.

Long-term satellite observations of the water levels of lakes are crucial to our understanding of lake hydrological basin systems. The Ice, Cloud, and Land Elevation satellite (ICESat) and ICESat-2 were employed to monitor the water level of Qinghai Lake in the hydrological basin. The median of absolute deviation (MAD) method was exploited to remove the outliers. The results confirmed that the MAD range of ICESat was from 0.0525 to 0.2470 m, and the range of σ was from 0.0778 to 0.3662 m; the MAD range of ICESat-2 was from 0.0291 to 0.0490 m, and the range of σ was from 0.0431 to 0.0726 m; ICESat-2 was less than that of ICESat. The reference ellipsoid and geoid transfer equations were applied to convert the water level to the World Geodetic System (WGS84) and Earth Gravitational Model 2008 (EGM2008) geoid. The water level, as derived from laser altimeters, was validated by the Xiashe Hydrological Station; with ICESat, the coefficient of association (R) was 0.8419, the root mean square error (RMSE) was 0.1449 m, and the mean absolute error (MAE) was 0.1144 m; with ICESat-2, the R was 0.6917, the RMSE was 0.0531 m, and the MAE was 0.0647 m. The water levels from ICESat-2 are much more accurate than those from ICESat. The two combined laser altimeters showed that the R was 0.9931, the RMSE was 0.1309 m, and the MAE was 0.1035 m. The water level rise was 3.6584 m from 2004 to 2020. The rising rate was 0.2287 m/a. The collaborative use of the ICESat-2 and ICESat satellites made it easier to obtain the lake water levels.

In order to anticipate residual errors and improve accuracy while reducing uncertainties, this work integrates the long short-term memory (LSTM) with the Soil and Water Assessment Tool (SWAT) to create a deep learning (DL) model that is guided by physics. By forecasting the residual errors of the SWAT model, the SWAT-informed LSTM model (LSTM-SWAT) differs from typical LSTM approaches that predict the streamflow directly. Through numerical tests, the performance of the LSTM-SWAT was evaluated with both LSTM-only and SWAT-only models in the Upper Heihe River Basin. The outcomes showed that the LSTM-SWAT performed better than the other models, showing higher accuracy and a lower mean absolute error (MAE = 3.13 m³/s). Sensitivity experiments further showed how the quality of the training dataset affects the performance of the LSTM-SWAT. The results of this study demonstrate how the LSTM-SWAT may improve streamflow prediction greatly by remote sensing and in situ observations. Additionally, this study emphasizes the need for detailed consideration of specific sources of uncertainty to further improve the predictive capabilities of the hybrid model.

Precipitation monitoring is important for earth system modeling and environmental management. Low spatial representativeness limits gauge measurements of rainfall and low spatial resolution limits satellite-derived rainfall. SM2RAIN-based products, which exploit the inversion of the water balance equation to derive rainfall from soil moisture (SM) observations, can be an alternative. However, the quality of SM data limits the accuracy of rainfall. The goal of this work was to improve the accuracy of rainfall estimation through merging multiple soil moisture (SM) datasets. This study proposed an integration framework, which consists of multiple machine learning methods, to use satellite and ground-based soil moisture observations to derive a precipitation product. First, three machine learning (ML) methods (random forest (RF), long short-term memory (LSTM), and convolutional neural network (CNN)) were used, respectively to generate three SM datasets (RF-SM, LSTM-SM, and CNN-SM) by merging satellite (SMOS, SMAP, and ASCAT) and ground-based SM observations. Then, these SM datasets were merged using the Bayesian model averaging method and validated by wireless sensor network (WSN) observations. Finally, the merged SM data were used to produce a rainfall dataset (SM2R) using SM2RAIN. The SM2R dataset was validated using automatic meteorological station (AMS) rainfall observations recorded throughout the Upper Heihe River Basin (China) during 2014–2015 and compared with other rainfall datasets. Our results revealed that the quality of the SM2R data outperforms that of GPM-SM2RAIN, Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS), ERA5-Land (ERA5) and multi-source weighted-ensemble Precipitation (MSWEP). Triple-collocation analysis revealed that SM2R outperformed China Meteorological Data and the China Meteorological Forcing Dataset. Ultimately, the SM2R rainfall product was considered successful with acceptably low spatiotemporal errors (RMSE = 3.5 mm, R = 0.59, and bias = −1.6 mm).

Land surface temperature (LST) plays a crucial role in Earth’s energy balance and ecosystems. Various gap-filling methods have been developed to reconstruct seamless LST datasets to deal with the effect of data gaps caused by cloud cover; however, existing studies mainly focus on LST reconstruction under clear-sky conditions, rather than generating actual cloud-impacted LST. This study treats MODIS cloud-free pixels as known sample points. The deep forest (DF) algorithm is employed to establish a nonlinear relationship model between Himawari-8 cumulative downward surface shortwave radiation (DSSR), AMSR2 brightness temperature (TB) data, and other influencing factors on the sample points, as well as LST. This model is applied to cloud-covered pixels to obtain the LST of the underlying pixels, thereby reconstructing the real MODIS LST under the cloud over the Yellow River source region. The feasibility of this approach lies in the fact that cumulative DSSR incorporates the impact of cloud coverage on incoming solar radiation, and there exists a correlation between AMSR2 TB data and LST. The reconstruction results for January, April, July, and October of 2021 were validated against in situ 0 cm LST measurements from five meteorological stations. The results show that the reconstructed LST exhibits high consistency with in situ measurements, with $R^{2}$ hof 0.86, bias of 0.62K, and RMSE of 4.48K. The results demonstrate the effectiveness of using DSSR and microwave data in LST reconstruction, accurately representing actual cloud-impacted LST.