Assessment of the Future Impact of Climate Change on the Hydrology of the Mangoky River, Madagascar Using ANN and SWAT

Abstract

The assessment of the impacts of climate change on hydrology is important for better water resources management. However, few studies have been conducted in semi-arid Africa, even less in Madagascar. Here we report, climate-induced future hydrological prediction in Mangoky river, Madagascar using an artificial neural network (ANN) and the soil and water assessment tool (SWAT). The current study downscaled two global climate models on the mid-term, noted the 2040s (2041–2050) and long-term, noted 2090s (2091–2099) under two shared socioeconomic pathways (SSP) scenarios, SSP 3–7.0 and SSP 5–8.5. Statistical indices of both ANN and SWAT showed good performance (R2 > 0.65) of the models. Our results revealed a rise in maximum temperature (4.26–4.69 °C) and minimum temperature (2.74–3.01 °C) in the 2040s and 2090s. Under SSP 3–7.0 and SSP 5–8.5, a decline in the annual precipitation is projected in the 2040s and increased the 2090s. This study found that future precipitation and temperature could significantly decrease annual runoff by 60.59% and 73.77% in the 2040s; and 25.18% and 23.45% in the 2090s under SSP 3–7.0 and SSP 5–8.5, respectively. Our findings could be useful for the adaptation to climate change, managing water resources, and water engineering.

Recently Emerging Trends in Big Data Analytic Methods for Modeling and Combating Climate Change Effects

“…Further comparison is needed to determine the more e cient approach to select the methods based on the processing and analysing tasks. More so, more dynamic updates are required by the developers of General Circulation Models (GCMs) to improve climate modeling resulting in high emissions [45].…”

Future Climate Change Impact on the Nyabugogo Catchment Water Balance in Rwanda

“…The SWAT model is a spatially distributed hydrological model that was designed to assist water resource managers in assessing the impacts of climate change, land use, and management approaches on water resources [34,35]. This model has been widely employed by researchers for watershed modeling and water resource management in watersheds with different climatic and topographic characteristics, owing to its user-friendly interface (ArcSWAT) and flexible data needs [27,36]; it has already been validated for various watershed scales in different climatic situations around the world, and it has worked well even in complex and data-poor watersheds [37]. The SWAT model also has the advantage of allowing the simulation of a variety of physical processes (e.g., hydrological, sediment, and contaminants) in a watershed.…”

“…During the rainy season (Figure 8c), less significant increases and decreases in precipitation were projected under SSP126 in both periods, which should result in increased runoff. However, a decrease was predicted, which could be associated with a significant increase in ET due to increased maximum and minimum temperatures [27,83]. Temperature effects tend to dominate in the 21st century under the high-emissions scenario, which had a significant impact on reducing runoff despite the predicted increase in precipitation during the rainy season [84,85].…”

“…Various hydrological models-including the Soil and Water Assessment Tool (SWAT), variable infiltration capacity (VIC), and MIKE SHE-have been applied to support the assessment of the impact of climate change on water resources under various environmental conditions and management techniques. With the advantage of having a lower number of input parameters compared to other modeling approaches, the SWAT is among the most popular models applied, and has proven its satisfactory accuracy in simulating the impact of climate change on different hydrological processes, in both long and short periods, under different climatic and soil conditions [25][26][27].…”

Is Climate Change Affecting the Monsoon Months in Pune, India?

“…They concluded that neural networks could efficiently forecast future evapotranspiration even with the constraint of having limited climate parameters as inputs, Additionally, they are commented that the accuracy could be significantly improved by addition of a greater number of inputs. Rabezanahary, et al [19] also focused their work on predicting the future precipitation and temperature at Mangoky River, Madagascar. 26 causative variables were chosen with the help of a linear measure (coefficient of correlation) calculated between the predictors and the desired output (Temperature and pressure).…”