Estimation of Rainfall by Neural Network Over a Neotropical Region (Estimativa De Chuvas Pela Rede Neural Sobre a Região Neotropical)

Abstract

Rainfall is the key element in regional water balance, and has direct influence over economic activity. Quantifying rainfall at spatial and temporal scales in regions where meteorological stations are scarce is important for agriculture, natural resource management and land-atmosphere interactions science. Thus, we evaluated neural network performance for rainfall estimates over Mato Grosso State located in the Brazilian Midwest region. A dataset of 12 meteorological stations was used to train the neural network, and then was run to perform estimates, which allowed comparing with TRMM satellite estimates. Rainfall estimates were performed by neural network as a function of latitude and longitude for model 1 (NN1), and latitude, longitude, and altitude for model 2 (NN2). In general, rainfall values were higher overestimated by NN1 in January (18.7%), and September (119.2%) than by NN2 in January (6.8%), and September (0%). While NN2 had rainfall pattern closer to TRMM both in January and in September, NN1 rainfall estimates captured a small amount of the rainfall pattern over Mato Grosso state. There was no higher difference between NN1 and NN2 rainfall estimates in January. On the other hand, rainfall estimates had better performance in NN2 than NN1 in September. Bad rainfall estimates using neural network in Mato Grosso state were due to (i) a short temporal dataset, (ii) few stations with poor spatial variability, (iii) few auxiliary variables to build neural network, which could better capture the rain phenomenon over Neotropical regions. The next step will be to analyze the rainfall and other climatic estimates performed by neural network for the whole year for several years on the Central-West Region of Brazil including other auxiliary variables besides latitude, longitude, and altitude.

Validation of rainfall data estimated by GPM satellite on Southern Amazon region

“…The Root Mean Square Error -RMSE (Equation 2) was also analyzed, indicating that the model presents failures in the comparison between the estimated and the measured values, and the Mean Absolute Error -MAE Equation 3, which indicates the absolute mean distance (deviation) between the estimated and measured values. In both errors, the values must be close to zero (Machado et al, 2015).…”

“…The data were processed on the basis of yearly and monthly averages. The relation between the measured values and the estimated ones was made through the Pearson "r" correlation index, the analysis of accuracy through Willmott "d" index (Equation 1), which links the distance of the estimated values in comparison with the observed ones, and its values vary between 0, for no matching, and 1, for perfect matching (Machado et al, 2015). The Root Mean Square Error -RMSE (Equation 2) was also analyzed, indicating that the model presents failures in the comparison between the estimated and the measured values, and the Mean Absolute Error -MAE Equation 3, which indicates the absolute mean distance (deviation) between the estimated and measured values.…”

Evaluation of methods for estimating atmospheric emissivity in Mato-Grossense Cerrado

“…Also were used Willmott's index of agreement (d), which indicates the estimation agreement level when compared with measured values (Willmott et al, 1985), the Pearson correlation coefficient (r), which indicates the correlation level between observed and estimated values, and the confidence coefficient or Camargo and Sentelhas performance (c). The value of d and r must varies from 0 to 1, indicating non-concordance and perfect concordance, respectively (Machado et al, 2015).…”

Assessment of Remote Sensing and Re-Analysis Estimates of Regional Precipitation over Mato Grosso, Brazil

“…In addition to macroscale phenomena, the biophysical characteristics of the surface, such as vegetation and geographic relief, also influence the distribution of precipitation in the state [8]. However, the current spatial distribution of the weather stations in Mato Grosso is not geographically representative of the entire extent of the state, and the accessibility to the data is also limited due to the high number of measurement failures from methodological, technical, and geographic issues [13].…”