Amphibian species detection in water reservoirs using artificial neural networks for ecology-friendly city planning

Planning cities regardless of natural resources has led to the existence of threats for several species that occupy an important place in local ecosystems. Constructing buildings, bridges, or motorways over water reservoirs is perilous for resident amphibians, which belong to one of the most fragile animal groups. An automated system that reliably identifies whether any amphibian species live in a water reservoir before construction in that region will help building inspectors during city planning and will ensure that citizens can enjoy the opportunities provided by nature. In this paper, an intelligent amphibian species detection system is developed using features extracted from GIS and satellite images. The presence of seven amphibian species is detected using an artificial neural network (ANN). Depending on the spatial features of the region, the proposed cascade-forward backpropagation neural network (CFBNN) model, a special type of ANN, determines which amphibian species live there to enable ecological precautions to be taken before construction starts and to preserve the biodiversity for the future health of the community. The results clearly demonstrate that the proposed approach significantly outperforms recently suggested strategies with more than 15% improvement on average. The performance of the system shows that the proposed detection approach can be a useful tool for smart and ecological city planning. •Using neural networks to analyze geographical locations via the features of remote images.•CFBNN classifier is proposed for amphibian existence detection.•Road or bridge planning in line with Environmental Impact Assessment Directive.•Eco-friendly urbanization plans are proposed.•This method outperforms others and can be adapted to other ecological issues.