Optimisation and interpretation of machine and deep learning models for improved water quality management in Lake Loktak.

Loktak Lake, one of the largest freshwater lakes in Manipur, India, is critical for the eco-hydrology and economy of the region, but faces deteriorating water quality due to urbanisation, anthropogenic activities, and domestic sewage. Addressing the urgent need for effective pollution management, this study aims to assess the lake's water quality status using the water quality index (WQI) and develop advanced machine learning (ML) tools for WQI assessment and ML model interpretation to improve pollution management decision making. The WQI was assessed using entropy-based weighting arithmetic and three ML models - Gradient Boosting Machine (GBM), Random Forest (RF) and Deep Neural Network (DNN) - were optimised using a grid search algorithm in the H2O Application Programming Interface (API). These models were validated by various metrics and interpreted globally and locally via Partial Dependency Plot (PDP), Accumulated Local Effect (ALE) and SHapley Additive exPlanations (SHAP). The results show a WQI range of 72.38-100, with 52.7% of samples categorised as very poor. The RF model outperformed GBM and DNN and showed the highest accuracy and generalisation ability, which is reflected in the superior R2 values (0.97 in training, 0.9 in test) and the lower root mean square error (RMSE). RF's minimal margin of error and reliable feature interpretation contrasted with DNN's larger margin of error and inconsistency, which affected its usefulness for decision making. Turbidity was found to be a critical predictive feature in all models, significantly influencing WQI, with other variables such as pH and temperature also playing an important role. SHAP dependency plots illustrated the direct relationship between key water quality parameters such as turbidity and WQI predictions. The novelty of this study lies in its comprehensive approach to the evaluation and interpretation of ML models for WQI estimation, which provides a nuanced understanding of water quality dynamics in Loktak Lake. By identifying the most effective ML models and key predictive functions, this study provides invaluable insights for water quality management and paves the way for targeted strategies to monitor and improve water quality in this vital freshwater ecosystem.

Applying deep learning to manage urban ecosystems in arid Abha, Saudi Arabia: Remote sensing-based modelling for ecological condition assessment and decision-making.

This study aims to quantitatively and qualitatively assess the impact of urbanisation on the urban ecosystem in the city of Abha, Saudi Arabia, by analysing land use changes, urbanisation processes and their ecological impacts. Using a multidisciplinary approach, a novel remote sensing-based urban ecological condition index (RSUSEI) will be developed and applied to assess the ecological status of urban surfaces. Therefore, the identification and quantification of urbanisation is important. To do so, we used hyper-tuned artificial neural network (ANN) as well as Land Cover Change Rate (LCCR), Land Cover Index (LCI) and Landscape Expansion Index (LEI). For the development of (RSUSEI), we have used four advanced models such as fuzzy Logic, Principle Component Analysis (PCA), Analytical Hierarchy Process (AHP) and fuzzy Analytical Hierarchy Process (FAHP) to integrate various ecological parameters. In order to obtain more information for better decision making in urban planning, sensitivity and uncertainty analyses based on a deep neural network (DNN) were also used. The results of the study show a multi-layered pattern of urbanisation in Saudi Arabian cities reflected in the LCCR, indicating rapid urban expansion, especially in the built-up areas with an LCCR of 0.112 over the 30-year period, corresponding to a more than four-fold increase in urban land cover. At the same time, the LCI shows a remarkable increase in 'built-up' areas from 3.217% to 13.982%, reflecting the substantial conversion of other land cover types to urban uses. Furthermore, the LEI emphasises the complexity of urban growth. Outward expansion (118.98 km2), Edge-Expansion (95.22 km2) and Infilling (5.00 km2) together paint a picture of a city expanding outwards while filling gaps in the existing urban fabric. The RSUSEI model shows that the zone of extremely poor ecological condition covers an area of 157-250 km2, while the natural zone covers 91-410 km2. The DNN based sensitivity analysis is useful to determine the optimal model, while the integrated models have lower input parameter uncertainty than other models. The results of the study have significant implications for the management of urban ecosystems in arid areas and the protection of natural habitats while improving the quality of life of urban residents. The RSUSEI model can be used effectively to assess urban surface ecology and inform urban management techniques.

Empowering real-time flood impact assessment through the integration of machine learning and Google Earth Engine: a comprehensive approach.

Floods cause substantial losses to life and property, especially in flood-prone regions like northwestern Bangladesh. Timely and precise evaluation of flood impacts is critical for effective flood management and decision-making. This research demonstrates an integrated approach utilizing machine learning and Google Earth Engine to enable real-time flood assessment. Synthetic aperture radar (SAR) data from Sentinel-1 and the Google Earth Engine platform were employed to generate near real-time flood maps of the 2020 flood in Kurigram and Lalmonirhat. An automatic thresholding technique quantified flooded areas. For land use/land cover (LULC) analysis, Sentinel-2's high resolution and machine learning models like artificial neural networks (ANN), random forests (RF) and support vector machines (SVM) were leveraged. ANN delivered the best LULC mapping with 0.94 accuracy based on metrics like accuracy, kappa, mean F1 score, mean sensitivity, mean specificity, mean positive predictive value, mean negative value, mean precision, mean recall, mean detection rate and mean balanced accuracy. Results showed over 600,000 people exposed at peak inundation in July-about 17% of the population. The machine learning-enabled LULC maps reliably identified vulnerable areas to prioritize flood management. Over half of croplands flooded in July. This research demonstrates the potential of integrating SAR, machine learning and cloud computing to empower authorities through real-time monitoring and accurate LULC mapping essential for effective flood response. The proposed comprehensive methodology can assist stakeholders in developing data-driven flood management strategies to reduce impacts.

Future groundwater potential mapping using machine learning algorithms and climate change scenarios in Bangladesh.

The aim of the study was to estimate future groundwater potential zones based on machine learning algorithms and climate change scenarios. Fourteen parameters (i.e., curvature, drainage density, slope, roughness, rainfall, temperature, relative humidity, lineament density, land use and land cover, general soil types, geology, geomorphology, topographic position index (TPI), topographic wetness index (TWI)) were used in developing machine learning algorithms. Three machine learning algorithms (i.e., artificial neural network (ANN), logistic model tree (LMT), and logistic regression (LR)) were applied to identify groundwater potential zones. The best-fit model was selected based on the ROC curve. Representative concentration pathways (RCP) of 2.5, 4.5, 6.0, and 8.5 climate scenarios of precipitation were used for modeling future climate change. Finally, future groundwater potential zones were identified for 2025, 2030, 2035, and 2040 based on the best machine learning model and future RCP models. According to findings, ANN shows better accuracy than the other two models (AUC: 0.875). The ANN model predicted that 23.10 percent of the land was in very high groundwater potential zones, whereas 33.50 percent was in extremely high groundwater potential zones. The study forecasts precipitation values under different climate change scenarios (RCP2.6, RCP4.5, RCP6, and RCP8.5) for 2025, 2030, 2035, and 2040 using an ANN model and shows spatial distribution maps for each scenario. Finally, sixteen scenarios were generated for future groundwater potential zones. Government officials may utilize the study's results to inform evidence-based choices on water management and planning at the national level.