Wetland Water Level Prediction Using Artificial Neural Networks—A Case Study in the Colombo Flood Detention Area, Sri Lanka

Abstract

Historically, wetlands have not been given much attention in terms of their value due to the general public being unaware. Nevertheless, wetlands are still threatened by many anthropogenic activities, in addition to ongoing climate change. With these recent developments, water level prediction of wetlands has become an important task in order to identify potential environmental damage and for the sustainable management of wetlands. Therefore, this study identified a reliable neural network model by which to predict wetland water levels over the Colombo flood detention area, Sri Lanka. This is the first study conducted using machine learning techniques in wetland water level predictions in Sri Lanka. The model was developed with independent meteorological variables, including rainfall, evaporation, temperature, relative humidity, and wind speed. The water levels measurements of previous years were used as dependent variables, and the analysis was based on a seasonal timescale. Two neural network training algorithms, the Levenberg Marquardt algorithm (LM) and the Scaled Conjugate algorithm (SG), were used to model the nonlinear relationship, while the Mean Squared Error (MSE) and Coefficient of Correlation (CC) were used as the performance indices by which to understand the robustness of the model. In addition, uncertainty analysis was carried out using d-factor simulations. The performance indicators showed that the LM algorithm produced better results by which to model the wetland water level ahead of the SC algorithm, with a mean squared error of 0.0002 and a coefficient of correlation of 0.99. In addition, the computational efficiencies were excellent in the LM algorithm compared to the SC algorithm in terms of the prediction of water levels. LM showcased 3–5 epochs, whereas SC showcased 34–50 epochs of computational efficiencies for all four seasonal predictions. However, the d-factor showcased that the results were not within the cluster of uncertainty. Therefore, the overall results suggest that the Artificial Neural Network can be successfully used to predict the wetland water levels, which is immensely important in the management and conservation of the wetlands.

Sensitivity Analysis of Parameters Affecting Wetland Water Levels: A Study of Flood Detention Basin, Colombo, Sri Lanka

“…These parameters directly and indirectly help in balancing the hydrological cycle, which impacts the wetland water levels. Higher coefficients of determination (R 2 ) can be found in many research studies for the relationship between those independent variations to wetland water levels [ 23 ]. This shows a strong relationship between these variables and the wetland water level.…”

“…On the other hand, the South Asian region lacks recent studies on wetland water level predictions. As per the authors’ knowledge, the first attempt in the context of Sri Lanka to develop a water level simulation model was initiated by Jayathilake et al [ 23 ] as an initial attempt. It investigated the applicability of ANNs to predict the water levels in a critical wetland in Colombo, Sri Lanka.…”

A Comprehensive Flood Risk Inundation Mapping and Hybrid Model for Flood Forecasting in the Panam River Basin

“…The partial dependence plots (PDP) also highlighted the model's sensitivity to elements like liquid intake depth and the share of quartz sand, emphasizing their importance. In the area of modeling wetland water levels, Jayathilake et al [8] located that the LM set of rules outperformed the SC set of regulations, handing over advanced consequences with average squared mistakes of 0.0002 and a correlation coefficient of 0.99. Furthermore, the LM algorithm demonstrated significantly better computational efficiency than the SC algorithm when predicting water levels.…”