The Ugii Nuur Lake is not only one of the small hydrologically closed lakes located in the Orkhon River Basin in Central Mongolia but also the most vulnerable area for global climate change. Therefore, this study aims to investigate the impacts of recent global climate change on the water surface area. The data we analyzed were various measured hydro-meteorological variables of the lake basin and the lake surface area, which was estimated from Landsat series satellite data from 1986 to 2018. The methods we used were Mann-Kendall (MK), Innovative trend analysis method (ITAM), Sen’s slope estimator test, correlation, and regression analysis. The variation of lake water surface area has a strong positive correlation with the change of the lake water level (r = 0.95). The Mann-Kendall trend analysis has indicated that under a significant decrease in total annual precipitation ( $\mathrm{Z}$ = −0.902) and inflow river discharge ( $\mathrm{Z}$ = −5.392) and a considerable increase in total annual evaporation ( $\mathrm{Z}$ = 4.385) and annual average air temperature ( $\mathrm{Z}$ = 4.595), the surface area of the Ugii Nuur Lake has decreased sharply ( $\mathrm{Z}$ = −6.021). The total annual evaporation (r = −0.64) and inflow river discharge (r = 0.67) were the essential hydro-meteorological factors affecting the surface area of the Ugii Nuur Lake. The lake surface area decreased by 13.5% in 2018 compared with 1986. In the near future, it is vital to conduct scientific studies considering the volume of lake water, groundwater, and the anthropogenic impact.

Many studies have been conducted on air pollution in Ulaanbaatar city. However, most have focused on the sources of pollutants and their characteristics and distribution. Although the location of the city subjects it to unavoidable natural conditions where air pollution accumulates during the cold season, nature-based solutions have not yet been considered in the projects implemented to mitigate air pollution levels. Therefore, this study aims to determine the combined influence of geography and atmospheric factors on cold season air pollution. The spatiotemporal variations in the variables were investigated using meteorological observation data from 1991 to 2020 in the different land-use areas. Then, atmospheric stagnation conditions and air pollution potential parameters were estimated from daily radiosonde data. Subsequently, the temporal variations in air pollutants were studied and correlated with estimates of the above parameters. In the Ulaanbaatar depression, the stable cold air lake (colder than −13.5 °C), windless (34–66% of all observations), and poor turbulent mixing conditions were formed under the near-surface temperature inversion layer in the cold season. Moreover, due to the mountain topography, the winds toward the city center from all sides cause polluted air to accumulate in the city center for long periods. Air pollution potential was categorized as very high and high (<4000 m²·s⁻¹), in the city in winter, indicating the worst air quality. Thus, further urban planning policy should consider these nature factors.

The relationship between reservoirs and naturally formed lakes in Mongolia has not been previously studied. This research explores potential future environmental impacts, both positive and negative, in western Mongolia. The study employs morphological analysis (MA), normalised difference water index (NDWI), volume analysis and statistical analysis of water. In the case of Airag Lake and an artificially created lake, temporal changes in lake surface area and volume exhibit inverse trends. The correlation between changes in lake area over time is highly negative (R = −0.96, p < 0.01 for the surface area), which is attributed to a decrease in Airag Lake’s area and volume during the lake water accumulation period from 2007 to 2011 and countered by an increase in Gegeen Lake’s area and volume. Conversely, the surface area of Khyargas Lake shows a strong positive correlation (R = 0.94, p < 0.0001) with Airag Lake’s area and a strong negative correlation (R = −0.88, p < 0.0001) with Gegeen Lake’s area during the period from 2007 to 2021. Based on satellite data, our findings suggest a negative relationship between changes in lake surface area and volume, indicating recent significant human impacts on lake water balance. This research explores the implications of hydropower dams and reservoirs in the region, as well as environmental concerns within the context of power production.

As an emerging remote sensing technology, Global Navigation Satellite System Reflectometry (GNSS-R) offers moderate penetration capabilities and supports all-weather observations. It has been widely applied in soil moisture retrieval. However, GNSS-R-based soil moisture inversion faces significant challenges due to the marked heterogeneity, complex feature associations, and difficulty in unified modeling among Delay-Doppler Map (DDM) imagery, time delay waveforms, and auxiliary features. To address these issues, this study introduces a multi-modal fusion strategy combined with a deep learning approach that possesses strong nonlinear modeling capabilities, and proposes a novel GNSS-R soil moisture retrieval model termed the Multi-modal Cross-Branch Fusion Network (MCBF-Net). MCBF-Net consists of three parallel branches designed to process different modalities of input data: a one-dimensional convolutional neural network (1D CNN) module for efficiently extracting features from time delay waveforms; a multi-scale fusion Transformer module for capturing the global features of DDM images; and a backpropagation (BP) neural network module that leverages its powerful nonlinear mapping capabilities to deeply learn complex patterns in the auxiliary data. Additionally, a multi-modal feature fusion module and a fusion loss function are embedded within the tri-branch architecture to ensure effective integration of features across modalities and to enhance the synergy among the network branches. Through this design, the model enables deep and comprehensive feature extraction and fusion from time delay waveforms, DDM imagery, and auxiliary information, significantly improving the accuracy of soil moisture retrieval. This study uses the Yellow River Delta region as the experimental area, focusing on the urgent needs of ecological environmental protection and sustainable agricultural development in the region. The soil moisture observation data provided by the Soil Moisture Active Passive (SMAP) satellite were used to validate the effectiveness of the proposed method. The retrieved results achieved a root mean square error (RMSE) of 0.0284 cm³/cm³ and a correlation coefficient (R) of 0.9232, indicating high accuracy and reliability. Furthermore, the study analyzed the spatiotemporal distribution characteristics of soil moisture in the Yellow River Delta, offering a feasible and efficient solution for regional-scale soil moisture inversion and refined monitoring.

Global navigation satellite system reflectometry (GNSS-R) is widely used for soil moisture retrieval. To mitigate heterogeneity between delay–doppler map (DDM) and auxiliary features and to impose physical constraints in fusion modeling, we propose a physics-guided cross-feature fusion network (PCF-Net) for the Yellow River Delta, comprising a multi-feature input, cross-feature fusion, and a physics-constrained retrieval module. Specifically, the multi-feature input module employs convolutional neural networks (CNNs) to extract spatial–local features from DDM and deep semantic information from auxiliary data, enabling structural alignment and unified embedding of heterogeneous modalities. The cross-feature fusion module adopts mamba-based cross-feature fusion (MCF) block and transformer-based cross-feature fusion (TCF) block to achieve bidirectional interaction and deep coupling between one-dimensional auxiliary features and DDM image features. The physics-constrained retrieval module constructs a physics-consistency loss between measured and simulated GNSS-R surface reflectivity to regularize the training process. We further construct a multi-source GNSS-R dataset from cyclone global navigation satellite system (CYGNSS), Tianmu-1, and fengyun-3E (FY-3E) and validate against soil moisture active passive (SMAP). The joint use of multi-source GNSS-R data markedly improves retrieval accuracy, achieving R of 0.9805 and RMSE of 0.0176 cm³/cm³, demonstrating effectiveness at the regional scale.

Extreme high flows can have negative economic, social, and ecological effects and are expected to become more severe in many regions due to climate change. Knowledge of maximum flow regimes and estimation of extreme rainfall is important, especially in ungauged dry regions, for planning and infrastructure development. In this study, we propose a regional method for estimating extreme flow regimes and modeled extreme rainfall using the extreme value theory, with examples from the Gobi region of Mongolia. The first step is to apply the Generalized Extreme Value (GEV) theory for the maximum rainfall data using 44-year observational data covering the period 1978–2022. Then, estimated rainfall with a 100-year return period is used for the empirical equation of the maximum flood calculation. As a result, most stations’ maximum rainfall follows a Fréchet distribution and 100-year return period rainfall values that range between 27.8–130.6 mm. The local reference value in the 100-year return period rainfall is defined as 90 mm for the whole Gobi region. Our results show that extremely high rainfall in the Gobi region has changed from −7% to 16%, leading to higher flood events. These findings further provide evidence for the maximum rainfall for flood calculation, climate change impact assessment, water resource planning, and management studies.