Integrating machine learning and geospatial data analysis for comprehensive flood hazard assessment.

Flooding is a major natural hazard worldwide, causing catastrophic damage to communities and infrastructure. Due to climate change exacerbating extreme weather events robust flood hazard modeling is crucial to support disaster resilience and adaptation. This study uses multi-sourced geospatial datasets to develop an advanced machine learning framework for flood hazard assessment in the Arambag region of West Bengal, India. The flood inventory was constructed through Sentinel-1 SAR analysis and global flood databases. Fifteen flood conditioning factors related to topography, land cover, soil, rainfall, proximity, and demographics were incorporated. Rigorous training and testing of diverse machine learning models, including RF, AdaBoost, rFerns, XGB, DeepBoost, GBM, SDA, BAM, monmlp, and MARS algorithms, were undertaken for categorical flood hazard mapping. Model optimization was achieved through statistical feature selection techniques. Accuracy metrics and advanced model interpretability methods like SHAP and Boruta were implemented to evaluate predictive performance. According to the area under the receiver operating characteristic curve (AUC), the prediction accuracy of the models performed was around > 80%. RF achieves an AUC of 0.847 at resampling factor 5, indicating strong discriminative performance. AdaBoost also consistently exhibits good discriminative ability, with AUC values of 0.839 at resampling factor 10. Boruta and SHAP analysis indicated precipitation and elevation as factors most significantly contributing to flood hazard assessment in the study area. Most of the machine learning models pointed out southern portions of the study area as highly susceptible areas. On average, from 17.2 to 18.6% of the study area is highly susceptible to flood hazards. In the feature selection analysis, various nature-inspired algorithms identified the selected input parameters for flood hazard assessment, i.e., elevation, precipitation, distance to rivers, TWI, geomorphology, lithology, TRI, slope, soil type, curvature, NDVI, distance to roads, and gMIS. As per the Boruta and SHAP analyses, it was found that elevation, precipitation, and distance to rivers play the most crucial roles in the decision-making process for flood hazard assessment. The results indicated that the majority of the building footprints (15.27%) are at high and very high risk, followed by those at very low risk (43.80%), low risk (24.30%), and moderate risk (16.63%). Similarly, the cropland area affected by flooding in this region is categorized into five risk classes: very high (16.85%), high (17.28%), moderate (16.07%), low (16.51%), and very low (33.29%). However, this interdisciplinary study contributes significantly towards hydraulic and hydrological modeling for flood hazard management.

Integrating fuzzy-AHP and GIS for solid waste disposal site selection in Kenitra province, NW Morocco.

Selecting an optimal solid waste disposal site is one of the decisive waste management issues because unsuitable sites cause serious environmental and public health problems. In Kenitra province, northwest Morocco, sustainable disposal sites have become a major challenge due to rapid urbanization and population growth. In addition, the existing disposal sites are traditional and inappropriate. The objective of this study is to suggest potential suitable disposal sites using fuzzy logic and analytical hierarchy process (fuzzy-AHP) method integrated with geographic information system (GIS) techniques. For this purpose, thirteen factors affecting the selection process were involved. The results showed that 5% of the studied area is considered extremely suitable and scattered in the central-eastern parts, while 9% is considered almost unsuitable and distributed in the northern and southern parts. Thereafter, these results were validated using the area under the curve (AUC) of the receiver operating characteristics (ROC). The AUC found was 57.1%, which is a moderate prediction's accuracy because the existing sites used in the validation's process were randomly selected. These results can assist relevant authorities and stakeholders for setting new solid waste disposal sites in Kenitra province.

Assessing river water quality for ecological risk in the context of a decaying river in India.

The decay of rivers and river water pollution are common problems worldwide. However, many works have been performed on decaying rivers in India, and the status of the water quality is still unknown in Jalangi River. To this end, the present study intends to examine the water quality of the Jalangi River to assess ecological status in both the spatial and seasonal dimensions. To depict the spatiality of ecological risks, 34 water samples were collected from the source to the sink of the Jalangi River with an interval of 10 km while 119 water samples were collected from a secondary source during 2012-2022 to capture the seasonal dynamics. In this work, the seasonality and spatiality of change in the river's water quality have been explored. This study used the eutrophication index (EI), organic pollution index (OPI), and overall index of pollution (OIP) to assess the ecological risk. The results illustrated that the values of OPI range from 7.17 to 588, and the values of EI exceed the standard of 1, indicating the critical situation of the ecological status of Jalangi River. The value of OIP ranges between 2.67 and 3.91 revealing the slightly polluted condition of the river water. The study signified the ecological status of the river is in a critical situation due to elevated concentrations of biological oxygen demand, chemical oxygen demand, and low concentrations of dissolved oxygen. The present study found that stagnation of water flow in the river, primarily driven by the eastward tilting of the Bengal basin, triggered water pollution and ecological risk. Moreover, anthropogenic interventions in the form of riverbed agriculture and the discharge of untreated sewage from urban areas are playing a crucial role in deteriorating the water quality of the river. This decay needs substantial attention from the various stakeholders in a participatory manner.

Towards understanding climate change: Impact of land use indices and drainage on land surface temperature for valley drainage and non-drainage areas.

The continuous increase of urbanization and industrialization brought various climatic changes, leading to global warming. The unavailability of meteorological data makes remotely sensed data important for understanding climate change. Therefore, the land surface temperature (LST) is critical in understanding global climate changes and related hydrological processes. The main objective of this work is to explore the dominant drivers of land use and hydrologic indices for LST in drainage and non-drainage areas. Specifically, the relationship between LST changes, land use, and hydrologic indices in Northeast Qena, Egypt, was investigated. The Landsat 5 and 8 imagery, Geographic Information System (GIS), and R-package were applied to identify the change detection during 2000-2021. The normalized difference between vegetation index (NDVI), bare soil index (BSI), normalized difference built-up, built-up index (BUI), modified normalized difference water index (MNDWI), and soil-adjusted vegetation index (SAVI) were employed. The non-drainage or mountain areas were found to be more susceptible to high LST values. The comprehensive analysis and assessment of the spatiotemporal changes of LST indicated that land use and hydrologic indices were driving factors for LST changes. Considerably, LST retrieved from the Landsat imaginary showed significant variation between the maximum LST during 2000 (44.82°C) and 2021 (50.74°C). However, NDBI has got less spread during the past (2000) with 10-13%. A high negative correlation was observed between the LST and NDVI, while the SAVI and LST positively correlated. The results of this study provide relevant information for environmental planning to local management authorities.

Climate change and future challenges to the sustainable management of the Iraqi marshlands.

The application of restoration plans for the Iraqi marshlands is encountering significant challenges due to water scarcity and the impacts of climate change. This paper assesses the impact of water scarcity on the possibility of continuing the application of restoration and sustainable management plans for the main marshlands in Iraq. This assessment was conducted based on the available data and expected situation of available water resources under climate change conditions until the year 2035. Additionally, a satellite image-based index model was prepared and applied for the period 2009-2020 to obtain the spatiotemporal distribution of the restored marshlands. The results show that the shortage in water resources and insufficient inundation rates prevented the adequate application of the restoration plans. Also, applying the scenarios of distributing the deficit equally over all water demand sectors (S1) and according to the percentage of demand for each sector (S2) shows that the expected deficit in available water for the three marshes by the years 2025 and 2035 will be approximately 25% and 32% for S1 and 9% for S2. Consequently, the considered marshes are expected to lose approximately 20 to 33% of their eligible restoration areas. Accordingly, looking for suitable alternatives to support the water resources of these marshes became a very urgent matter and/or recourse to reduce the areas targeted by inundation and being satisfied with the areas that can be sustainable and maintain the current status of the rest of the regions as an emerging ecosystem characterized by lands that are inundated every few years. Accordingly, steps must be urged to develop plans and programs to maintain the sustainability of these emerging ecosystems within the frameworks of climate change and the conditions of scarcity of water resources and water and air pollution to ensure that they are not lost in the future.

Classification of precipitation types in Poland using machine learning and threshold temperature methods.

The phase in which precipitation falls-rainfall, snowfall, or sleet-has a considerable impact on hydrology and surface runoff. However, many weather stations only provide information on the total amount of precipitation, at other stations series are short or incomplete. To address this issue, data from 40 meteorological stations in Poland spanning the years 1966-2020 were utilized in this study to classify precipitation. Three methods were used to differentiate between rainfall and snowfall: machine learning (i.e., Random Forest), daily mean threshold air temperature, and daily wet bulb threshold temperature. The key findings of this study are: (i) the Random Forest (RF) method demonstrated the highest accuracy in rainfall/snowfall classification among the used approaches, which spanned from 0.90 to 1.00 across all stations and months; (ii) the classification accuracy provided by the mean wet bulb temperature and daily mean threshold air temperature approaches were quite similar, which spanned from 0.86 to 1.00 across all stations and months; (iii) Values of optimized mean threshold temperature and optimized wet bulb threshold temperature were determined for each of the 40 meteorological stations; (iv) the inclusion of water vapor pressure has a noteworthy impact on the RF classification model, and the removal of mean wet bulb temperature from the input data set leads to an improvement in the classification accuracy of the RF model. Future research should be conducted to explore the variations in the effectiveness of precipitation classification for each station.

Improving PM2.5 prediction in New Delhi using a hybrid extreme learning machine coupled with snake optimization algorithm.

Fine particulate matter (PM2.5) is a significant air pollutant that drives the most chronic health problems and premature mortality in big metropolitans such as Delhi. In such a context, accurate prediction of PM2.5 concentration is critical for raising public awareness, allowing sensitive populations to plan ahead, and providing governments with information for public health alerts. This study applies a novel hybridization of extreme learning machine (ELM) with a snake optimization algorithm called the ELM-SO model to forecast PM2.5 concentrations. The model has been developed on air quality inputs and meteorological parameters. Furthermore, the ELM-SO hybrid model is compared with individual machine learning models, such as Support Vector Regression (SVR), Random Forest (RF), Extreme Learning Machines (ELM), Gradient Boosting Regressor (GBR), XGBoost, and a deep learning model known as Long Short-Term Memory networks (LSTM), in forecasting PM2.5 concentrations. The study results suggested that ELM-SO exhibited the highest level of predictive performance among the five models, with a testing value of squared correlation coefficient (R2) of 0.928, and root mean square error of 30.325 µg/m3. The study's findings suggest that the ELM-SO technique is a valuable tool for accurately forecasting PM2.5 concentrations and could help advance the field of air quality forecasting. By developing state-of-the-art air pollution prediction models that incorporate ELM-SO, it may be possible to understand better and anticipate the effects of air pollution on human health and the environment.

Land cover and crop types mapping using different spatial resolution imagery in a Mediterranean irrigated area.

Crop type identification is critical for agricultural sustainability policy development and environmental assessments. Therefore, it is important to obtain their spatial distribution via different approaches. Medium-, high- and very high-resolution optical satellite sensors are efficient tools for acquiring this information, particularly for challenging studies such as those conducted in heterogeneous agricultural fields. This research examined the ability of four multitemporal datasets (Sentinel-1-SAR (S1), Sentinel-2-MSI (S2), RapidEye (RE), and PlanetScope (PS)) to identify land cover and crop types (LCCT) in a Mediterranean irrigated area. To map LCCT distribution, a supervised pixel-based classification is adopted using Support Vector Machine with a radial basis function kernel (SVMRB) and Random Forest (RF). Thus, LCCT maps were generated into three levels, including six (Level I), ten (Level II), and fourteen (Level III) classes. Overall, the findings revealed high overall accuracies of >92%, >83%, and > 81% for Level I, Level II, and Level III, respectively, except for Sentinel-1. It was found that accuracy improves considerably when the number of classes decreases, especially when cropland or non-cropland classes are grouped into one. Furthermore, there was a similarity in performance between S2 alone and S1S2. PlanetScope LCCT classifications outperform other sensors. In addition, the present study demonstrated that SVM achieved better performances against RF and can thereby effectively extract LCCT information from high-resolution imagery as PlanetScope.

Predicting potential reforestation areas by Quercus ilex (L.) species using machine learning algorithms: case of upper Ziz, southeastern Morocco.

The selection of appropriate areas for reforestation remains a complex task because of influence by several factors, which requires the use of new techniques. Based on the accurate outcomes obtained through machine learning in prior investigations, the current study evaluates the capacities of six machine learning techniques (MLT) for delineating optimal areas for reforestation purposes specifically targeting Quercus ilex, an important local species to protect soil and water in upper Ziz, southeast Morocco. In the initial phase, the remaining stands of Q. ilex were identified, and at each site, measurements were taken for a set of 12 geo-environmental parameters including slope, aspect, elevation, geology, distance to stream, rainfall, slope length, plan curvature, profile curvature, erodibility, soil erosion, and land use/land cover. Subsequently, six machine learning algorithms were applied to model optimal areas for reforestation. In terms of models' performance, the results were compared, and the best were obtained by Bagging (area under the curve (AUC) = 0.98) and Naive Bayes (AUC = 0.97). Extremely favorable areas represent 8% and 17% of the study area according to Bagging and NB respectively, located to the west where geological unit of Bathonian-Bajocian with low erodibility index (K) and where rainfall varies between 250 and 300 mm/year. This work provides a roadmap for decision-makers to increase the chances of successful reforestation at lower cost and in less time.

Groundwater vulnerability to pollution assessment: an application of geospatial techniques and integrated IRN-DEMATEL-ANP decision model.

This study evaluated the susceptibility to groundwater pollution using a modified DRASTIC model. A novel hybrid multi-criteria decision-making (MCDM) model integrating Interval Rough Numbers (IRN), Decision Making Trial and Evaluation Laboratory (DEMATEL), and Analytical Network Process (ANP) was used to investigate the interrelationships between critical hydrogeologic factors (and determine their relative weights) via a novel vulnerability index based on the DRASTIC model. The flexibility of GIS in handling spatial data was employed to delineate thematic map layers of the hydrogeologic factors and to improve the DRASTIC model. The hybrid MCDM model results show that net recharge (a key hydrogeologic factor) had the highest priority with a weight of 0.1986. In contrast, the topography factor had the least priority, with a weight of 0.0497. A case study validated the hybrid model using Anambra State, Nigeria. The resultant vulnerability map shows that 12.98% of the study area falls into a very high vulnerability class, 31.90% falls into a high vulnerability, 23.52% falls into the average vulnerability, 21.75% falls into a low vulnerability, and 9.85% falls into very low vulnerability classes, respectively. In addition, nitrate concentration was used to evaluate the degree of groundwater pollution. Based on observed nitrate concentration, the modified DRASTIC model was validated and compared to the traditional DRASTIC model; interestingly, the spatial model of the modified DRASTIC model performed better. This study is thus critical for environmental monitoring and implementing appropriate management interventions to protect groundwater resources against indiscriminate sources of pollution.

Zoning the suitability of the western Mekong Delta for paddy rice cultivation and aquaculture under current and future environmental conditions.

Ca Mau and Kien Giang, the two provinces of the Mekong Delta bordering the Gulf of Thailand, are facing major environmental challenges affecting the agriculture and aquaculture sectors upon which many livelihoods in this region depend on. This study maps the suitability of these two provinces for paddy rice cultivation and shrimp farming according to soil characteristics and current and future environmental conditions for variables found to significantly influence the yield of those two sectors, i.e., the level of saltwater intrusion, water availability for rainfed agriculture, and the length of the growing period. Future environmental conditions were simulated using the MIKE 11 hydrodynamic model forced by four hydrodynamic scenarios, each one representing different extents of saltwater intrusion during both the dry and rainy seasons, while also considering the availability of water resources for rainfed agriculture. The suitability zoning was performed using a GIS-based analytic hierarchy process (AHP) approach, resulting in the categorisation of the land according to four suitability levels for each sector. The analysis reveals that paddy rice cultivation will become more suitable to Kien Giang province while shrimp farming will be more suitable to Ca Mau province if the simulated future environmental conditions materialise. A suitability analysis is essential for optimal utilisation of the land. The approach presented in this study will inform the regional economic development master plan and provide guidance to other delta regions experiencing severe environmental changes and wishing to consider potential future climatic and sea level changes, and their associated impacts, in their land use planning.

Region of freshwater influence (ROFI) and its impact on sediment transport in the lower Mekong Delta coastal zone of Vietnam.

The delta of the Mekong River is one of the largest in the world, with the Mekong River carrying a large amount of sediments in its Region of Freshwater Influence (ROFI). This study investigates the flow structure and movement of both suspended and bedload sediments in the ROFI of the Lower Mekong Delta (LMD) in order to identify areas prone to sediment accretion and erosion. This is accomplished by applying the three-dimensional Coastal and Regional Ocean COmmunity (CROCO) model and then calculating the sediment budget of different stretches of the coastline. The model outputs, depicting areas experiencing sediment accretion and erosion along the coastline of the LMD, are then compared against observations obtained during the period 1990-2015 and demonstrate the ability of the model to identify areas particularly prone to erosion and where preventive actions against coastal erosion should focus.

A modified approach to quantify aquifer vulnerability to pollution towards sustainable groundwater management in Irrigated Indus Basin.

The quality of groundwater in the study watershed has worsened because of industrial effluents and residential wastes from the urbanized cities; therefore, there is an important need to explore the aquifer vulnerability to pollution for sustainable groundwater management in the Irrigated Indus Basin (IIB). This study proposed a novel methodology to quantify groundwater vulnerability using two fully independent methodologies: the first by reintroducing an improved recharge factor (R) map and the second by incorporating three different weight and rating schemes into a traditional DRASTIC framework to improve the performance of the DRASTIC approach. In the current study, we composed a recharge map from Soil and Water Assessment Tool (SWAT) output (namely SWAT recharge map) with a drainage density map to retrieve an improved composite recharge map (SWAT-CRM). SWAT-CRM along with other thematic layers was combined using weightage overlay analysis to prepare the maps of groundwater vulnerability index (VI). The weight scale (w) and rating scale (r) were assigned based on a survey of available literature, and we then amended them using the analytical hierarchy process (AHP) and a probability frequency ratio (PFR) technique. Results depicted that the region under high groundwater vulnerability was found to be 5-22% using traditional recharge maps, while those are 9-23% using improved SWAT-CRM. The area under the curve (AUC) revealed that groundwater vulnerability zones predicted with SWAT-CRM outperformed the DRASTIC model applied with the traditional recharge map. Groundwater electrical conductivity (EC) was>2500 mS/cm in the high groundwater vulnerability zones, while it was <1000 mS/cm in the low groundwater vulnerability zones. The outcomes of this study can be used to improve the sustainability of the groundwater resources in IIB through proper land-use management practices.

Developing a new approach for design support of subsurface constructed wetland using machine learning algorithms.

Knowing the effluent quality of treatment systems in advance to enable the design of treatment systems that comply with environmental standards is a realistic strategy. This study aims to develop machine learning - based predictive models for designing the subsurface constructed wetlands (SCW). Data from the SCW literature during the period of 2009-2020 included 618 sets and 10 features. Five algorithms namely, Random forest, Classification and Regression trees, Support vector machines, K-nearest neighbors, and Cubist were compared to determine an optimal algorithm. All nine input features including the influent concentrations, C:N ratio, hydraulic loading rate, height, aeration, flow type, feeding, and filter type were confirmed as relevant features for the predictive algorithms. The comparative result revealed that Cubist is the best algorithm with the lowest RMSE (7.77 and 21.77 mg.L-1 for NH4-N and COD, respectively) corresponding to 84% of the variance in the effluents explained. The coefficient of determination of the Cubist algorithm obtained for NH4-N and COD prediction from the test data were 0.92 and 0.93, respectively. Five case studies of the application of SCW design were also exercised and verified by the prediction model. Finally, a fully developed Cubist algorithm-based design tool for SCW was proposed.

Integrating water quality index, GIS and multivariate statistical techniques towards a better understanding of drinking water quality.

Groundwater is considered as an imperative component of the accessible water assets across the world. Due to urbanization, industrialization and intensive farming practices, the groundwater resources have been exposed to large-scale depletion and quality degradation. The prime objective of this study was to evaluate the groundwater quality for drinking purposes in Mewat district of Haryana, India. For this purpose, twenty-five groundwater samples were collected from hand pumps and tube wells spread over the entire district. Samples were analyzed for pH, electrical conductivity (EC), total dissolved solids (TDS), total hardness (TH), turbidity, total alkalinity (TA), cations and anions in the laboratory using the standard methods. Two different water quality indices (weighted arithmetic water quality index and entropy weighted water quality index) were computed to characterize the groundwater quality of the study area. Ordinary Kriging technique was applied to generate spatial distribution map of the WQIs. Four semivariogram models, i.e. circular, spherical, exponential and Gaussian were used and found to be the best fit for analyzing the spatial variability in terms of weighted arithmetic index (GWQI) and entropy weighted water quality index (EWQI). Hierarchical cluster analysis (HCA), principal component analysis (PCA) and discriminant analysis (DA) were applied to provide additional scientific insights into the information content of the groundwater quality data available for this study. The interpretation of WQI analysis based on GWQI and EWQI reveals that 64% of the samples belong to the "poor" to "very poor" bracket. The result for the semivariogram modeling also shows that Gaussian model obtains the best fit for both EWQI and GWQI dataset. HCA classified 25 sampling locations into three main clusters of similar groundwater characteristics. DA validated these clusters and identified a total of three significant variables (pH, EC and Cl) by adopting stepwise method. The application of PCA resulted in three factors explaining 69.81% of the total variance. These factors reveal how processes like rock water interaction, urban waste discharge and mineral dissolution affect the groundwater quality.

Prediction of groundwater nitrate concentration in a semiarid region using hybrid Bayesian artificial intelligence approaches.

Nitrate is a major pollutant in groundwater whose main source is municipal wastewater and agricultural activities. In the present study, Bayesian approaches such as Bayesian generalized linear model (BGLM), Bayesian regularized neural network (BRNN), Bayesian additive regression tree (BART), and Bayesian ridge regression (BRR) were used to model groundwater nitrate contamination in a semiarid region Marvdasht watershed, Fars province, Iran. Eleven groundwater (GW) nitrate conditioning factors have been taken as input parameters for predictive modeling. The results showed that the Bayesian models used in this study were all competent to model groundwater nitrate and the BART model with R2 = 0.83 was more efficient than the other models. The result of variable importance showed that potassium (K) has the highest importance in the models followed by rainfall, altitude, groundwater depth, and distance from the residential area. The results of the study can support the decision-making process to control and reduce the sources of nitrate pollution.

Using machine learning methods for supporting GR2M model in runoff estimation in an ungauged basin.

Estimating monthly runoff variation, especially in ungauged basins, is inevitable for water resource planning and management. The present study aimed to evaluate the regionalization methods for determining regional parameters of the rainfall-runoff model (i.e., GR2M model). Two regionalization methods (i.e., regression-based methods and distance-based methods) were investigated in this study. Three regression-based methods were selected including Multiple Linear Regression (MLR), Random Forest (RF), and M5 Model Tree (M5), and two distance-based methods included Spatial Proximity Approach and Physical Similarity Approach (PSA). Hydrological data and the basin's physical attributes were analyzed from 37 runoff stations in Thailand's southern basin. The results showed that using hydrological data for estimating the GR2M model parameters is better than using the basin's physical attributes. RF had the most accuracy in estimating regional GR2M model's parameters by giving the lowest error, followed by M5, MLR, SPA, and PSA. Such regional parameters were then applied in estimating monthly runoff using the GR2M model. Then, their performance was evaluated using three performance criteria, i.e., Nash-Sutcliffe Efficiency (NSE), Correlation Coefficient (r), and Overall Index (OI). The regionalized monthly runoff with RF performed the best, followed by SPA, M5, MLR, and PSA. The Taylor diagram was also used to graphically evaluate the obtained results, which indicated that RF provided the products closest to GR2M's results, followed by SPA, M5, PSA, and MLR. Our finding revealed the applicability of machine learning for estimating monthly runoff in the ungauged basins. However, the SPA would be recommended in areas where lacking the basin's physical attributes and hydrological information.

Machine learning algorithm-based risk assessment of riparian wetlands in Padma River Basin of Northwest Bangladesh.

Wetland risk assessment is a global concern especially in developing countries like Bangladesh. The present study explored the spatiotemporal dynamics of wetlands, prediction of wetland risk assessment. The wetland risk assessment was predicted based on ten selected parameters, such as fragmentation probability, distance to road, and settlement. We used M5P, random forest (RF), reduced error pruning tree (REPTree), and support vector machine (SVM) machine learning techniques for wetland risk assessment. The results showed that wetland areas at present are declining less than one-third of those in 1988 due to the construction of the dam at Farakka, which is situated at the upstream of the Padma River. The distance to the river and built-up area are the two most contributing drivers influencing the wetland risk assessment based on information gain ratio (InGR). The prediction results of machine learning models showed 64.48% of area by M5P, 61.75% of area by RF, 62.18% of area by REPTree, and 55.74% of area by SVM have been predicted as the high and very high-risk zones. The results of accuracy assessment showed that the RF outperformed than other models (area under curve: 0.83), followed by the SVM, M5P, and REPTree. Degradation of wetlands explored in this study demonstrated the negative effects on biodiversity. Therefore, to conserve and protect the wetlands, continuous monitoring of wetlands using high resolution satellite images, feeding with the ecological flow, confining built up area and agricultural expansion towards wetlands, and new wetland creation is essential for wetland management.