Search Results (5,046)

Deep learning has garnered increasing attention in human activity detection due to its advantages, such as not relying on expert knowledge and automatic feature extraction. However, the existing deep learning-based approaches are primarily confined to recognizing specific types of human activities, which hinders scientific decision-making and comprehensive environmental protection. Therefore, there is an urgent need to develop a deep learning model to address multiple-type human activity detection with finer-resolution images. In this study, we proposed a new multi-task learning model (named PE-MLNet) to simultaneously achieve change detection and land use classification in GF-6 bitemporal images. Meanwhile, we also designed a pooling enhancement module (PEM) to accurately capture multi-scale change details from the bitemporal feature maps through combining differencing and concatenating branches. An independent annotated dataset at Yellow River Delta was taken to examine the effectiveness of PE-MLNet. The results showed that PE-MLNet exhibited obvious improvements in both detection accuracy and detail handling compared with other existing methods. Further analysis uncovered that the areas of buildings, roads, and oil depots has obviously increased, while the farmland and wetland areas largely decreased over the five years, indicating an expansion of human activities and their increased impacts on natural environments. Full article

Interferometric Synthetic Aperture Radar (InSAR) technology has emerged as a vital tool for monitoring surface deformation due to its high accuracy and spatial resolution. With the rapid economic development of Nanchang, extensive infrastructure development and construction activities have significantly altered the urban landscape. Underground excavation and groundwater extraction in the region are potential contributors to surface deformation. This study utilized Sentinel-1 satellite data, acquired between September 2018 and May 2023, and applied the Permanent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) technique to monitor surface deformation in Nanchang’s urban area. The findings revealed that surface deformation rates in the study area range from −10 mm/a to 6 mm/a, with the majority of regions remaining relatively stable. Approximately 99.9% of the monitored points exhibited deformation rates within −5 mm/a to 5 mm/a. However, four significant subsidence zones were identified along the Gan River and its downstream regions, with a maximum subsidence rate reaching 9.7 mm/a. Historical satellite imagery comparisons indicated that certain subsidence areas are potentially associated with construction activities. Further analysis integrating subsidence data, monthly precipitation, and groundwater depth revealed a negative correlation between surface deformation in Region A and rainfall, with subsidence trends aligning with groundwater level fluctuations. However, such a correlation was not evident in the other three regions. Additionally, water level data from the Xingzi Station of Poyang Lake showed that only Region A’s subsidence trend closely corresponds with water level variations. We conducted a detailed analysis of the spatial distribution of soil types in Nanchang and found that the soil types in areas of surface deformation are primarily Semi-hydromorphic Soils and Anthropogenic Soils. These soils exhibit high compressibility, making them prone to compaction and significantly influencing surface deformation. This study concludes that localized surface deformation in Nanchang is primarily driven by urban construction activities and the compaction of artificial fill soils, while precipitation also has an impact in certain areas. Full article

This study examines the responses of soil organic carbon (SOC) pools and their components to agricultural water drainage in paddy fields, with a focus on the wetland–paddy field ecotone of Xingkai Lake, a transboundary lake shared by China and Russia. Field investigations targeted three representative wetland vegetation types: Glyceria spiculosa (G), Phragmites australis (P), and Typha orientalis (T), across drainage durations ranging from 0 to over 50 years. SOC fractions, including light fraction organic carbon (LFOC), heavy fraction organic carbon (HFOC), dissolved organic carbon (DOC), and microbial biomass carbon (MBC), were systematically analyzed. The results revealed that SOC components in T and P wetlands steadily increased with drainage duration, whereas those in G wetlands exhibited a fluctuating pattern. SOC dynamics were primarily driven by LFOC, while MBC displayed species-specific variations. Correlation analyses and structural equation modeling (SEM) demonstrated that soil physicochemical properties, such as total nitrogen and moisture content, exerted a stronger influence on SOC fractions than microbial biomass. Overall, water drawdown significantly altered SOC dynamics, with distinct responses observed across vegetation types and wetland ages. This study provides critical data and theoretical insights for optimizing carbon sequestration and hydrological management in wetland–paddy field systems. Full article

Manual forestland classification methods, which rely on predetermined scoring criteria and subjective interpretation, are commonly used but suffer from limitations such as high labor costs, complexity, and lack of scalability. This study proposes an innovative machine learning-based approach to forestland classification, utilizing a Support Vector Machine (SVM) model to automate the classification process and enhance both efficiency and accuracy. The main contributions of this work are as follows: A machine learning model was developed using integrated data from the Third National Land Survey of China, including forestry, grassland, and wetland datasets. Unlike previous approaches, the SVM model is optimized with Grid Search (GS), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO) to automatically determine classification parameters, overcoming the limitations of manual rule-based methods. The performance of the SVM model was evaluated using confusion matrices, classification accuracy, and Matthews Correlation Coefficient (MCC). A comprehensive comparison under different optimization techniques revealed significant improvements in classification accuracy and generalization ability over manual classification systems. The experimental results demonstrated that the GA-SVM model achieved classification accuracies of 98.83% (test set) and 99.65% (overall sample), with MCC values of 0.9796 and 0.990, respectively, outpacing other optimization algorithms, including Grid Search (GS) and Particle Swarm Optimization (PSO). The GA-SVM model was applied to classify public welfare forestland in Kunyu City, yielding detailed classifications across various forestland categories. This result provides a more efficient and accurate method for large-scale forestland management, with significant implications for future land use assessments. The findings underscore the advantages of the GA-SVM model in forestland classification: it is efficient, accurate, and easy to operate. This study not only presents a more reliable alternative to conventional rule-based and manual scoring methods but also sets a precedent for using machine learning to automate and optimize forestland classification in future applications. Full article

Urban non-point source (NPS) pollution is an important risk factor that leads to the deterioration of urban water quality, affects human health, and destroys the ecological balance of the water environment. Reasonable risk prevention and control of urban NPS pollution are conducive to reducing the cost of pollution management. Therefore, based on the theory of “source–sink” in landscape ecology, combined with the minimum cumulative resistance (MCR) model, this study considered the influence of geographic-environment factors in Shenyang’s built-up area on pollutants in the process of entering the water body under the action of surface runoff, and evaluated its risk. The results indicated that the highest pollution loads are generated by road surfaces. High-density residential zones and industrial zones are the main sources of urban NPS pollution. Impervious surface ratios and patch density were the dominant environmental factors affecting pollutant transport, with contributions of 56% and 40%, respectively. The minimum cumulative resistance to urban NPS pollution transport is significantly and positively correlated with the distance from water bodies and roads. Higher risk areas are mainly concentrated in the center of built-up areas and roads near the Hun River. Green spaces, business zones, public service zones, development zones, and educational zones demonstrate the highest average risk index values, exceeding 29. In contrast, preservation zones showed the lowest risk index (7.3). Compared with the traditional risk index method, the method proposed in this study could accurately estimate the risk of urban NPS pollution and provide a new reference for risk assessments of urban NPS pollution. Full article

Globally, 14–20% of peatlands are affected by agricultural activities, which account for about one-third of global greenhouse gas emissions from farmlands. However, how agricultural activities such as nitrogen fertilization affect peatlands’ CH₄, CO₂ and N₂O emission patterns and their resulting warming effects needs to be improved and complemented. Here, we elucidate the characterization of CH₄, CO₂ and N₂O emissions from the soil surface and different depths of the soil profile during the growing season of agricultural peatlands for over 50 years and the mechanisms of their resulting global warming potential (GWP) impact through field monitoring and molecular techniques. The 100-year GWP of peatlands increased by 1200% with N fertilization of 260 kg N ha⁻¹ yr⁻¹. At the soil surface, N fertilization increased CO₂ and N₂O emissions by 111% and 2600%, respectively, although CH₄ emissions decreased by 87%. In the soil profile, N fertilization had a significant effect on CO₂ from 0 to 60 cm, resulting in an increase in CO₂ concentrations of 14–132%, whereas the top 30 cm of soil was the zone of significant N fertilization effects, with CH₄ concentrations decreasing by 49–95% and N₂O concentrations increasing by 22–26%. Elevated soil pH and NH₄⁺ were the key environmental factors influencing CH₄, CO₂ and N₂O emissions and their resulting increase in GWP. These results suggest that agricultural N fertilization led to a change in the contributor to the GWP of peatlands from CH₄ to N₂O, especially in the top 30 cm of soil. This study helps to provide theoretical support for the development of effective peatland management strategies. Full article

Ensuring the ecological water requirements (EWR) suitable for wetlands are upheld is essential for maintaining the stability and health of their ecosystems, a challenge faced by wetlands globally. However, previous studies on EWRs estimation lack a comprehensive consideration of wetlands and still suffer from the problem of rough time scales. Prior studies have predominantly concentrated on its core and buffer zones, neglecting a comprehensive analysis of the wetland’s entirety and failing to account for the seasonal variations in EWRs. To fill this gap, we proposed a novel framework for estimating EWRs wetland’s entirety to guide the development of dynamic water replenishment strategies. The grey prediction model was used to project the wetland area under different scenarios and designed water replenishment strategies. We then applied this framework in a key wetland conservation area in China, the Momoge Wetland, which is currently facing issues of areal shrinkage and functional degradation due to insufficient EWRs. Our findings indicate that the maximum, optimal, and minimum EWRs for the Momoge Wetland are 24.14 × 10⁸ m³, 16.65 × 10⁸ m³, and 10.88 × 10⁸ m³, respectively. The EWRs during the overwintering, breeding, and flood periods are estimated at 1.92 × 10⁸ m³, 5.39 × 10⁸ m³, and 8.73 × 10⁸ m³, respectively. Based on the predicted wetland areas under different climatic conditions, the necessary water replenishment volumes for the Momoge Wetland under scenarios of dry-dry-dry, dry-dry-normal, dry-normal-dry, and normal-normal-normal are calculated to be 0.70 × 10⁸ m³, 0.49 × 10⁸ m³, 0.68 × 10⁸ m³, and 0.36 × 10⁸ m³, respectively. In years characterized by drought, the current water replenishment projects are inadequate to meet the wetland’s water needs, highlighting the urgent need for the implementation of multi-source water replenishment techniques to enhance the effectiveness of these interventions. The results of this study provide insights for annual and seasonal water replenishment planning and multi-source water management of wetlands with similar problems as the Momoge Wetland. With these new insights, our novel framework not only advances knowledge on the accuracy of wetland ecological water requirement assessment but also provides a scalable solution for global wetland water resource management, helping to improve the ecosystem’s adaptability to future climate changes. Full article

Vegetation is a fundamental component of terrestrial ecosystems, and accurately assessing the effects of seasonal climate variations, extreme weather events, and land use changes on vegetation dynamics is crucial. The Ganjiang River Basin (GRB), a key region for water conservation and recharge in southeastern China, has experienced significant land use changes and variable climate in the past. However, comprehensive evaluations of how these changes have impacted vegetation remain limited. To address this gap, we used machine learning models (random forest and XGBoost) to assess the impact of seasonal and extreme climate variables, land cover, topography, soil properties, atmospheric CO₂, and night-time light intensity on vegetation dynamics. We found that the annual mean NDVI showed a slight increase from 1990 to 1999 but has decreased significantly over the last 8 years. XGBoost was better than the RF model in simulating the NDVI when using all five types of data source (R² = 0.85; RMSE = 0.04). The most critical factors influencing the NDVI were forest and cropland ratio, followed by soil organic carbon content, elevation, cation exchange capacity, night-time light intensity, and CO₂ concentration. Spring minimum temperature was the most important seasonal climate variable. Both linear and nonlinear relationships were identified between these variables and the NDVI, with most variables exhibiting threshold effects. These findings underscore the need to develop and implement effective land management strategies to enhance vegetation health and promote ecological balance in the region. Full article

As a habitat for waterbirds, wetlands are key to their survival, reproduction and development. Waterbirds usually prefer breeding, wintering and resting in fixed locations. Siberian cranes (Grus leucogeranus), which are highly dependent on wetlands, have long fed on farmland at migratory stopover sites. To explore the reason for this phenomenon, the time budgets of Siberian crane populations stopping over on farmland or in wetland habitats were studied and compared in this study. The results showed that the farmlands visited by the Siberian cranes are rich in food resources and have experienced low levels of disturbance. The temporal distribution of feeding behavior on farmland (53.50%) was greater than that in wetland habitats (31.96%). The variations in warning, flying and walking behavior on farmland were less than those in wetlands. The feeding efficiency on farmland was significantly greater than that in wetlands. Therefore, Siberian cranes transiting the Songnen Plain leave wetland habitats and stop over on farmland, representing a behavior that occurs more than just occasionally. Instead, they change their foraging habitat choices based on the optimal foraging theory. As a transit feeding area for Siberian cranes, farmland poses a significant risk, and the restoration of wetland habitats and food resources is still needed. This study can provide theoretical support for the conservation of rare and endangered species (the Siberian crane) and the management of stopover sites. Full article

Increasing nitrogen (N) addition induces soil nutrient imbalances and is recognized as a major regulator of soil microbial communities. However, how soil bacterial abundance, diversity, and community composition respond to exogenous N addition in nutrient-poor and generally N-limited regions remains understudied. In this study, we investigated the effects of short-term exogenous N additions on soil bacterial communities using quantitative polymerase chain reaction (PCR) and Illumina Miseq sequencing in an in situ N addition field experiment. The results showed that a low nitrogen addition increased the observed species (Sobs) of the bacterial community, and with the increased nitrogen addition, the Sobs of bacteria gradually decreased, especially the unique OTUs. The relative abundance of Proteobacteria, Actinobacteria, and Gemmatimonadetes increased with increasing nitrogen addition, whereas the relative abundance of Chloroflexi and Firmicutes decreased. Soil properties play an important role in bacterial community structure at phylum or genus levels. Short-term nitrogen addition increased the proportion of nodes from Actinobacteria and Proteobacteria in the co-occurrence network and enhanced the stability of the microbial network. Actinobacteria may play an important role in constructing the network. Our study aims to explore the effects of nitrogen addition on the diversity, composition, and structure of soil bacterial communities in nutrient-poor areas caused by ecological disturbances. Full article

Resolving the status of soil carbon with land cover is critical for addressing the impacts of climate change arising from land cover conversion in boreal regions. However, many conventional inferential approaches inadequately gauge statistical significance for this issue, due to limited sample sizes or skewness of soil properties. This study aimed to address this drawback by adopting inferential approaches suitable for smaller samples sizes, where normal distributions of soil properties were not assumed. A two-step inference process was proposed. The Kruskal–Wallis (KW) test was first employed to evaluate disparities amongst soil properties. Generalized estimating equations (GEEs) were then wielded for a more thorough analysis. The proposed method was applied to soil samples (n = 431) extracted within the southern transition zone of the boreal forest (49°–50° N, 80°40′–84° W) in northern Ontario, Canada. Sites representative of eight land cover types and seven dominant tree species were sampled, investigating the total carbon (C), carbon-to-nitrogen ratio (C:N), clay percentage, and bulk density (BD). The KW test analysis corroborated significance (p-values < 0.05) for median differences between soil properties across the cover types. GEEs supported refined robust statistical evidence of mean differences in soil C between specific tree species groupings and land covers, particularly for black spruce (Picea mariana) and wetlands. In addition to the proposed method, the results of this study provided application for the selection of appropriate predictors for C with digital soil mapping. Full article

The potential of biochar to mediate shifts in soil microbial communities caused by polycyclic aromatic hydrocarbon (PAH) stress in farmland, thus assisting in the bioremediation of contaminated soil, remains uncertain. This study introduced wheat straw biochars generated at 300 °C (W300) and 500 °C (W500) at varying levels (1% and 2% w/w) into agricultural soil contaminated with phenanthrene at 2.5 and 25 mg/kg. The aim was to investigate their effects on microbial community structure and phenanthrene degradation by indigenous microbes. Biochar application in both slightly (PLS) and heavily (PHS) contaminated soils increased overall microbial/bacterial biomass, preserved bacterial diversity, and selectively enriched certain bacterial genera, which were suppressed by phenanthrene stress, through sorption enhancement and biotoxicity alleviation. The abundances of PAH-degrading genera and nidA degradation gene were promoted by biochar, especially W300, in PHS due to soil nutrient improvement, enhancing phenanthrene biodegradation. However, in PLS, biochar, particularly W500, inhibited their abundance due to a reduction in phenanthrene bioavailability to specific degraders, thus hindering phenanthrene biodegradation. These findings suggest that applying wheat straw biochar produced at appropriate temperatures can benefit soil microbial ecology and facilitate PAH elimination, offering a sustainable strategy for utilizing straw resources and safeguarding soil health and agricultural product quality. Full article

Under the combined influences of climate change and human activities, the western Jilin (WJ) Province, as a typical ecologically fragile area, has experienced ecological degradation and resource depletion. Therefore, it is urgently needed to assess its ecological carrying capacity (ECC) to provide scientific support for regional ecological protection and resource management. This study integrated the “Pressure-State-Response” (P-S-R) model with the “production, living, and ecological spaces” (PLES) conceptual model to construct a comprehensive evaluation indicator system for ECC. The indicator weights were calculated using a Bayesian BWM-CRITIC-CWDF linear combination method, and the spatial–temporal distribution of ECC was then assessed using an improved TOPSIS and gray relational analysis (GRA). This evaluation model overcomes the limitations of traditional methods in weight allocation, indicator correlation, and non-linear effects, providing a more accurate, reliable, and objective assessment of ECC. Furthermore, a bivariate spatial autocorrelation model was applied to reveal the interaction between the “coupling coordination degree (CCD) of PLES” and ECC. The results indicate that the ECC value was divided into a period of decline (2000–2010) and a period of growth (2010–2020); spatially, the ECC level transitioned from a high-west, low-east to a high-east, low-west pattern. This change was primarily driven by factors such as fertilizer usage, per capita GDP, and per capita output. The “CCD of PLES” and ECC indicated positive spatial correlation, primarily forming “high-high” and “high-low” clusters. This study provides a reliable evaluation index system and an evaluation model for evaluating ECC in WJ. The findings provide a theoretical foundation for the region’s sustainable development and offer valuable insights for ecological carrying capacity research. Full article

Ecosystems, water supplies, and tourism all benefit from the protection of forest regions. All the above affect the possibility for tourism to prosper in forested areas. Tikvara Nature Park (TNP) has significant tourist potential for the development of specific and sustainable forms of tourism because it has direct contact with the Danube River, which forms the Upper Danube Region. This nature park has a significant forested area, inhabited by rare species of flora and fauna. In addition, there are wetlands, which are inhabited by rare species of birds, aquatic animals, and plants. Ecological and socio-cultural sustainability are the subjects of research in this article. It was possible to observe all possibilities for the growth of tourism based on nature by analyzing sustainable tourism by applying an extended PoS study method. The results of this research indicate that the two examined dimensions have a significant impact on the state and perspective of tourism development in this nature park. Also, sustainable tourism has an impact on the satisfaction of respondents through ecological and socio-cultural factors of the destination. Analysis of the results indicates that the respondents are ready to harmonize their activities with ecological principles in this protected area. Researching these two dimensions of sustainable tourism development (STuD) is important for tourism planning, growth, and nature protection control. This study’s significant results demonstrate the importance of environmental and socio-cultural elements for tourism development (ToD), and their substantial influence on tourism sustainability (ToS) and local and visitor satisfaction. Plans for the growth of sustainable tourism might be significantly influenced by research findings. Full article

Scyphiphora hydrophyllacea is an endangered mangrove species in China. Over-exploitation and coastal development have drastically reduced its distribution and population, now limited to the Qingmei Port (Sanya) and the Qinglan Port (Wenchang). Despite its critical status, research on its ecological roles remains limited. This study examines the characteristics of S. hydrophyllacea communities and their relationship with soil properties. A total of 17 species from 11 families and 14 genera were recorded. TWINSPAN classification identified two distinct community types: the Qinglan Port community and the Qingmei Port community. Significant biodiversity differences were found only in the tree layer, with no differences in shrub or herbaceous layers. The importance value of S. hydrophyllacea within the arbor layer exhibited variability across the two communities, serving as an associated species in the Qinglan Port community and as a dominant species in the Qingmei Port community, suggesting potential barriers to its natural regeneration. Redundancy analysis (RDA) revealed that key soil factors influencing S. hydrophyllacea’s distribution include electrical conductivity (EC), total phosphorus (TP), total nitrogen (TN), soil organic content (SOC), and carbon/nitrogen ratio (C/N). We propose that high soil salinity and nitrogen deficiency may act as key factors limiting the natural regeneration of S. hydrophyllacea. Full article