Floods and erosion are natural hazards that present a substantial risks to both human and ecological systems, particularly in coastal regions. Flooding occurs when water inundates typically dry areas, causing widespread damage, while erosion gradually depletes soil and rock through processes driven by water and wind. This study proposes an innovative approach that integrates Deep Neural Decision Forest (DeepNDF), Feedforward Neural Network (FNN), autoencoders, and Bidirectional Recurrent Neural Networks (Bi-RNN) models for flood prediction, enhanced through transfer learning for erosion mapping in coastal environments. Utilizing multi-source datasets from the United States Geological Survey (USGS), Climate Hazards Group InfraRed Precipitation with Station (CHIRPS), the National Algerian Institute of Cartography, and Sentinel-2 imagery, the key conditioning factors using Geographic Information System (GIS) were generated. The conditioning factors included elevation, slope, flow direction, curvature, distance from rivers, distance from roads, hillshade, topographic wetness index (TWI), stream power index (SPI), geology, and land use/land cover (LULC), as well as rainfall. To ensure the modeling reliability, the performance was rigorously evaluated using multiple statistical metrics, including the Area Under the Curve-Receiver Operating Characteristic (AUC-ROC), Precision, Recall, and F1 Score. The DeepNDF model achieved the highest performance for flood prediction with an AUC-ROC of 0.97, Precision of 0.93, Recall of 0.92, and an F1 Score of 0.925, while the transfer learning approach significantly improved erosion prediction, reaching an AUC-ROC of 0.92, Precision of 0.90, Recall of 0.92, and an F1 Score of 0.91. The analysis indicated that flood risks predominantly affected rangeland (18.68%) and bare ground (20.48%), while cropland was found to face the highest erosion risk, affecting approximately 3,471 km2. This research advances predictive modelling in hydrology and environmental science, providing valuable insights for disaster mitigation and resilience planning strategies in coastal areas.

Determining and characterising locations vulnerable to flooding can help in reducing damage and the number of fatalities. During the monsoon season, East India's Subarnarekha River frequently floods to a significant degree. In current work, we suggest a unique hybrid strategy for preparing the entire catchment's Flood Susceptibility Mapping (FSM). The study area's FSM was conducted by considering 10 flood conditioning factors utilising the Best-Worst Method (BWM) and a multi-parametric Analytical Hierarchy Process (AHP) as per expert knowledge. Meanwhile, the proposed strategy incorporates a Decision Making Trial and Evaluation Laboratory (DEMATEL) for examining causal linkages and dependencies between different elements affecting the flooding process. Several statistical matrices were used to compare the suggested strategy of BWM and AHP. Based on our findings, we concluded that the integration of DEMATEL with AHP and BWM (ID BWM, ID AHP) was more effective than alternative strategies. The findings show that out of 10 flood conditioning factors, slope, elevation, distance from the river, drainage density, Topographic wetness Index (TWI), Land Use Land Cover (LULC), Normalised Difference Vegetation Index (NDVI), precipitation, soil texture, and curvature, factors that have the biggest effects on the local flooding phenomenon are elevation, slope, precipitation, and distance from the river. For validating the efficacy of the flood susceptibility map, Area under the Receiver Operating Characteristic Curve (AUC-ROC) was adopted and demonstrated, showing a pretty high accuracy of (0.92 or 92% and 0.94 or 94%) for ID AHP and ID BWM, respectively. Our research findings provide a highly affordable and useful answer to the flooding problems of basin Subarnarekha.

In the context of climate change, rainstorm events are becoming increasingly frequent. In particular, on the Loess Plateau, heavy rainstorms are the primary cause of soil erosion. This study investigated and analysed different types of soil erosion hotspots and influencing factors in small watersheds under different rainstorm events in different areas of the Loess Plateau. The results indicate that the erosion intensities of rills, gullies, landslides and collapses ranged from 13600-46244, 1982-772201, 1163-172153 t km-2 and 1867-94985 t km-2, respectively. Newly constructed terraces exhibited an erosion intensity 1.6 times greater than that of old terraces, while terraces constructed before the rainy season in the current year exhibited an erosion damage intensity 2.6 times greater than that of terraces constructed after the rainy season in the previous year. In addition, under rainstorm conditions, landslides represented the most severe type of erosion in the watersheds, with the maximum amount of erosion accounting for more than 90 % of the total erosion amount, followed by gully or collapse erosion, with the collapse of terrace risers as the main contributor. Slope cultivation land, unpaved roads, terrace risers, and valley slopes below the gully shoulder line were identified as erosion hotspot areas. Rainstorm erosion was significantly influenced by the land use type and slope, which explained 14.2 %-41.5 % and 9.7 %-15.1 %, respectively, of the total variance in erosion intensity. We suggest that soil erosion prevention and control efforts on the Loess Plateau should focus on landslides on valley slopes below gully shoulder lines, followed by gullies on unpaved roads and the collapse of terraced fields. Drainage ditches and water cellars should be constructed above the gully shoulder line and on the inside of roads and terraces, thereby reducing erosion. Our research is crucial for optimizing and adjusting watershed management measures and preventing rainstorm erosion disasters.

The Earth is currently experiencing severe economic and social consequences as a result of frequent floods. This study is crucial for effective risk management and mitigation, protecting lives and property from potential flood damage in the Deme watershed. This study endeavors to assess the efficacy of a logistic regression model in generating a flood susceptibility map for the Deme watershed in Ethiopia. Fourteen factors contributing to flooding were considered, including digital elevation model, slope, aspect, profile curvature, plane curvature, Topographic Position Index (TPI), Topographic Roughness Index (TRI), flow direction, Topographic WetnessIindex (TWI), distance to the river, rainfall, land use/land cover (LULC), Normalized Difference Vegetation Index (NDVI), and soil type. The receiver operating characteristic (ROC) curve method was employed to validate the model. The area under the curve (AUC) values for the model were determined to be 81% for the training dataset and 82% for the validation dataset, indicating its effectiveness in delineating flood-prone areas. The findings revealed that 18% of the watershed is very highly susceptible to flooding, 19% exhibits high susceptibility, 18% shows moderate susceptibility, while 20 and 24% have low and very low susceptibility, respectively. This research provides insights into comprehensive flood prevention and urban development strategies. HIGHLIGHTS center dot Flood susceptibility is determined by historical flood patterns and their influencing factors. center dot Logistic regression can be used to map flood-susceptible areas in a small watershed. center dot A multicollinearity test is necessary to ensure a linear relationship in flood conditioning factors. center dot Factors with high multicollinearity should be removed from models to improve prediction accuracy.

Floods in Iran lead to significant human and financial losses annually. Identifying flood-prone regions is imperative to minimize these damages. This study aims to pinpoint flood-susceptible areas in the Great Karun Plain using remote sensing data, Google Earth Engine (GEE), and machine learning techniques. For the analysis, Landsat 8 data from April 8, 2019, and multiple variables including actual evapotranspiration, aspect, soil bulk density, clay content, climate water deficit, elevation, NDVI, land cover, Palmer Drought Severity Index, reference evapotranspiration, precipitation accumulation, sand content, soil moisture, minimum temperature, and maximum temperature were employed. These variables were utilized in the machine learning process to establish flood susceptibility zones. During the machine learning process, the base flow data of the Karun River was extracted from the Landsat image. A total of 19,335 samples were incorporated into the machine learning procedure using techniques such as MARS, CART, TreeNet, and RF. The model assessment criteria encompassed ROC, sensitivity, specificity, overall accuracy, F1score and mean sensitivity. Results indicated that the TreeNet technique yielded the most promising outcomes among the machine learning algorithms with ROC values of 0.965 for test data. The characteristic criterion reached 91.2%, while the overall accuracy criterion stood at 91.12%. The model's average sensitivity was 90.81%, and F1score was 63.51% for this technique. Additionally, analysis of the relative importance of independent variables highlighted that factors like vegetation cover (0.37), cumulative precipitation (0.23), soil water deficit (0.12), drought intensity (0.12), and landscapes (0.1) exerted a more pronounced influence on flooded areas compared to other variables.

More information is needed to fully comprehend how acid mine drainage (AMD) affects the phototransformation of antibiotic resistant bacteria (ARB) and antibiotic resistance genes (ARGs) in karst water and sewage -irrigated farmland soil with abundant carbonate rocks (CaCO 3 ) due to increasing pollution of AMD formed from pyrite (FeS 2 ). The results showed FeS 2 accelerated the inactivation of ARB with an inactivation of 8.7 log. Notably, extracellular and intracellular ARGs and mobile genetic elements (MGEs) also experienced rapid degradation. Additionally, the pH of the solution buffered by CaCO 3 significantly influenced the photo -inactivation of ARB. The Fe 2 + in neutral solution was present in Fe(II) coordination with strong reducing potential and played a crucial role in generating center dot OH (7.0 mu M), which caused severe damage to ARB, ARGs, and MGEs. The center dot OH induced by photo -Fenton of FeS 2 posed pressure to ARB, promoting oxidative stress response and increasing generation of reactive oxygen species (ROS), ultimately damaging cell membranes, proteins and DNA. Moreover, FeS 2 contributed to a decrease in MIC of ARB from 24 mg/L to 4 mg/L. These findings highlight the importance of AMD in influencing karst water and sewage -irrigated farmland soil ecosystems. They are also critical in advancing the utilization of FeS 2 to inactivate pathogenic bacteria.

The Cape Bounty Arctic Watershed Observatory (CBAWO), Melville Island, Nunavut (74 degrees 55 ' N, 109 degrees 34 ' W) was established in 2003 to examine Arctic ecosystem processes that would be impacted by climate warming and permafrost degradation. This paper provides a synthesis of how remote sensing has contributed to biogeophysical modelling and monitoring at the CBAWO from 2003 to 2023. Given the location and isolated nature of the CBAWO in the Canadian High Arctic, remote sensing data and derivatives have been instrumental for studies examining ecosystem structure and function at local and landscape scales. In combination with field measurements, remote sensing data facilitated mapping and modelling of vegetation types, % vegetation cover and aboveground phytomass, soil moisture, carbon exchange rates, and permafrost degradation and disturbance. It has been demonstrated that even in an environment with limited vegetation cover and phytomass, spectral vegetation indices (e.g., the normalized difference vegetation index) are able to model various biogeophysical variables. These applications are feasible for research sites such as the CBAWO using high spatial resolution remote sensing data across the visible, infrared, and microwave regions of the electromagnetic spectrum. Furthermore, as the satellite record continues to expand, we will gain a greater understanding of the impacts arising from the expected continued warming at northern latitudes. Although the logistics for research in the Arctic remain challenging, today's technologies (e.g., high spatial resolution satellite remote sensing, automated in situ sensors and data loggers, and wireless communication systems) can support a host of scientific endeavours in the Arctic (and other remote sites) through modelling and monitoring of biogeophysical variables and Earth surface processes with limited but critical field campaigns. The research synthesized here for the CBAWO highlights the essential role of remote sensing of terrestrial ecosystems in the Canadian Arctic.

Land-use change may significantly influence streamflow. The semi-empirical model PhosFate was used to analyze the impact of land use and climate change on streamflow by choosing the Guishui watershed as a pilot site and then expanding, applying it to all of North China. The Guishui watershed (North Beijing, China) has experienced a dramatic decline in its streamflow in recent decades. Parallel to this, significant land-use change has happened in this area; afforestation programs have increased forest cover from 41% (1980) to 59% (2013) and a similar increase in forest cover can also be observed in North China. Managing flow decline requires separating climatic and direct human-influenced effects. The results showed the following: (1) Afforestation is a major factor that decreased total flow in the Guishui watershed from 1996 to 2014; total flow increased by around 24% more than the actual dataset in the constant scenario (no afforestation) and decreased by 5% more than the actual dataset in the forest scenario (all agriculture land use transferred to forests). (2) When forest coverage increases, the Qinghai-Tibet Plateau and the Loess Plateau are the most sensitive areas regarding total flow in North China; the total flow change rate increased by up to 25% in these two areas when land use shifted from sparse vegetation to mixed forests. After analyzing the contributions of these two factors, we formulated recommendations on future afforestation practices for North China. In the central-north and northwest districts, the annual precipitation is under 520 mm and 790 mm, respectively, and the practice of afforestation should be more carefully planned to prevent severe damage to streams. This research also proved that the PhosFate model can be used in North China, which would be a practical tool for watershed management.

Changes in land use and land cover (LULC) are becoming recognized as critical to sustainability research, particularly in the context of changing landscapes. Soil erosion is one of the most important environmental challenges today, particularly in developing countries like Ethiopia. The objective of this study was evaluating the dynamics of soil loss, quantifying sediment yield, and detecting soil erosion hotspot fields in the Boyo watershed. To quantify the soil erosion risks, the Revised Universal Soil Loss Equation (RUSLE) model was used combined with remote sensing (RS) and geographic information system (GIS) technology, with land use/land cover, rainfall, soil, and management approaches as input variables. The sediment yield was estimated using the sediment delivery ratio (SDR) method. In contrast to a loss in forest land (1.7 %), water bodies (3.0 %), wetlands (1.5 %), and grassland (1.7 %), the analysis of LULC change (1991-2020) showed a yearly increase in the area of cultivated land (1.4 %), built-up land (0.8 %), and bare land (3.5 %). In 1991, 2000, and 2020, respectively, the watershed's mean annual soil loss increases by 15.5, 35.9, and 38.3 t/ha/y. Approximately 36 cm of the watershed's economically productive topsoil was lost throughout the study's twenty-nine-year period (1991-2020). According to the degree of erosion, 16 % of the watershed was deemed seriously damaged, while 70 % was deemed slightly degraded. Additionally, it is estimated for the year 2020 that 74,147.25 t/ y of sediment (8.52 % of the total annual soil loss of 870,763.12 t) reach the Boyo watershed outlet. SW4 and SW5 were the two sub-watersheds with the highest erosion rates, requiring immediate conservation intervention to restore the ecology of the Boyo watershed.

Human actions can damage the ecosystems and affect the services depending on them, with ample detrimental consequences. In earlier studies, the Conservation Use Potential (PCU) framework proved useful in assessing the capacity for aquifer recharge, suitable land uses and resistance to erosion at the river basin scale. On the other hand, the joint analysis of PCU and land uses allowed identifying the adequacy of current uses in relation to suitability (natural uses) in various basins. This was especially useful from the management perspective in basins with environmental conflicts, where current uses differed from suitability, because the PCU indicated how and where the conflicts should be mitigated. Besides the use as management tool, the PCU has potential to shed light over environmental issues such as ecosystem services, but that was not tempted so far. The aim of this work was therefore to bridge that knowledge gap and frame the PCU ' s application from the standpoint of Ecosystem Services (ES) assessment. We demonstrated how the PCU could be used to improve provision (recharge), support (sustainable agriculture) and regulation (resistance to erosion) services in a specific basin with land use conflicts (the Upper Rio das Velhas basin, located in Minas Gerais, Brazil), through the planning of suitable uses. It was noted that the studied basin is mostly composed of Very Low, Low and Medium potentials. These classes occur because steep slopes, fragile soils and lithologies with high denudation potential and low nutrient supply dominate in the basin. On the other hand, urban sprawl has a negative impact on all ES, while maintaining agricultural areas with appropriate management can effectively regulate erosion. As per the current results, the premise of using the PCU as joint management -environmental tool was fully accomplished, and is recommended a basis for public policy design and implementation in Brazil and elsewhere.