Information about mosquito activity is in demand these days because more people are engaging in outdoor activities in metropolitan settings. Predicting mosquito activity is also essential for regulating human safety and health. High spatial and temporal variability, however, make it difficult to accurately predict mosquito abundances, which reduces the accuracy of general mechanistic models of mosquito abundances. It is required to create a more straightforward and lightweight mosquito abundance forecast model as a result. In this study, we evaluated the effectiveness of the artificial neural network (ANN), a well-liked empirical model, for predicting mosquito abundance.
The outcomes demonstrated that the ANN model and the MLR model's performances were nearly identical in terms of R and root mean square error (RMSE). In contrast to MLR, the ANN model was able to forecast the high variability. The ANN model's sensitivity analysis revealed that it adequately explained the relationships between the input variables and mosquito abundances. In conclusion, ANNs have the capacity to forecast changes in mosquito populations (especially the extreme values), and they can do so better than conventional statistical methods.
<h3>What is a
rtificial neural network?</h3>
Computing systems inspired by the biological neural networks that make up animal brains are known as artificial neural networks (ANNs), also known as neural networks (NNs), or even more simply, neural nets.
To learn more about artificial neural network from the given link:
brainly.com/question/25653113
#SPJ4
