Application of Artificial Neural Network and Information Entropy Theory to Assess Rainfall Station Distribution: A Case Study from Colombia

Abstract

An assessment of the rainfall station distribution in the mountainous area of the Regional Autonomous Corporation of Cundinamarca (CAR, for its acronym in Spanish), Colombia, was conducted by applying concepts from information entropy and artificial neural networks (ANNs). This study was divided into two phases: first, a classification of the meteorological stations using two-dimensional self-organizing maps; second, the evaluation of the performance of the ANN by applying concepts of information entropy. Three scenarios were raised for the classification of the meteorological stations by adjusting the number of neurons in the output layer. A high number of neurons in the output layer were obtained, causing the model to over-fit while emphasizing differences amid patterns. When comparing the results of the scenarios, the permanence of certain characteristics and features was found in the system, validating the model classification. Subsequently, the results of the first scenario were used to evaluate the entropy of the historical series. Finally, the results show that the area of study presents a lack of information due to the uncertainty associated with the probabilistic arrangement, which can be corrected with the developed model. Consequently, some recommendations for the redesign of the rainfall are provided.

Scales and Historical Evolution: Methods to Reveal the Relationships between Ecosystem Service Bundles and Socio-Ecological Drivers—A Case Study of Dalian City, China

“…With advancements in the understanding of ES bundles, scholars have introduced the self-organizing map (SOM) method to quantify the distribution of ES bundles [ 19 , 20 , 21 ]. SOM advantageously combines the capacities of dimensionality reduction with cluster-analysis capabilities and, due to this, is widely recognized in environmental science [ 22 , 23 ]. Currently, the application of ES bundles is mainly focused on ES trade-offs and synergies [ 24 ], regionally dominant ESs, ecological-function zoning [ 25 ], landscape planning and management [ 10 ], etc.…”

Journal of Water and Land Development

“…To study the spatial variability of rainfall, there is a wide variety of literature and different methodologies used to understand or establish a distribution pattern, authors such as GARRIDO-ARÉVALO et al [2020], with historical records, have applied concepts from information entropy and artificial neural networks (ANNs) model for assessment of the rainfall station distribution. In that study, meteorological stations were classified for the first time using two-dimensional self-organising maps, raising three scenarios by adjusting the number of neurons in the output layer, then evaluated the performance of the ANNs by applying concepts of information entropy.…”