Abstract:
Tis study presents results for urban food susceptibility mapping (FSM) using image-based 2D-convolutional neural networks
(2D-CNN). Te model input multiparametric spatial data comprised of land-useland-cover (LULC), digital elevation model
(DEM), and the topographic and hydrologic conditioning derivatives, precipitation, and soil types. Te implemented dropout
regularization 2D-CNN with ReLU activation function, categorical cross-entropy loss function, and AdaGrad optimizer produced
the case study area FSM with overall accuracy (OA) of 82.5%. Te image-based 2D-CNN outperformed the multilayer perceptron
(MLP) neural network by 18.4% in terms of overall accuracy and with corresponding lower MAE and higher F1-measures of
10.9% and 0.989, as compared to 25.6% and 0.877, respectively, for MLP-ANN results. Te accuracy of the 2D-CNN that produced
FSM map and the model efciency were evaluated using area under the ROC curve (AUC) with respective success and prediction
rates of 0.827 and 0.809. Using image-based 2D-CNN, 27% of the 247.7 km2 of the studied area was mapped with a high risk of
fooding, with MLP-ANN overestimating the degree of high food risk by 4.7%. Based on the gain ratio index analysis of the food
conditioning factors (FCFs), the most signifcant FCFs were LULC (18.5%), precipitation (14.9%), proximity to river (13.3%), and
elevation (12.4%). Soil types contributed 8.6%, slope 9.1%, and the DEM-derived hodological conditioning indicators contributed
23.2%. Te study results demonstrate that in urban areas with scarce hydrological monitoring networks, the use of image-based
2D-CNN with multiparametric spatial data can produce high-quality food susceptibility maps for food management in urban
environments.