Air quality assessment and pollution forecasting using artificial neural networks in Metropolitan Lima-Peru

Abstract

The prediction of air pollution is of great importance in highly populated areas because it directly impacts both the management of the city’s economic activity and the health of its inhabitants. This work evaluates and predicts the Spatio-temporal behavior of air quality in Metropolitan Lima, Peru, using artificial neural networks. The conventional feedforward backpropagation known as Multilayer Perceptron (MLP) and the Recurrent Artificial Neural network known as Long Short-Term Memory networks (LSTM) were implemented for the hourly prediction of $$\hbox {PM}_{10}$$ PM 10 based on the past values of this pollutant and three meteorological variables obtained from five monitoring stations. The models were validated using two schemes: The Hold-Out and the Blocked-Nested Cross-Validation (BNCV). The simulation results show that periods of moderate $$\hbox {PM}_{10}$$ PM 10 concentration are predicted with high precision. Whereas, for periods of high contamination, the performance of both models, the MLP and LSTM, were diminished. On the other hand, the prediction performance improved slightly when the models were trained and validated with the BNCV scheme. The simulation results showed that the models obtained a good performance for the CDM, CRB, and SMP monitoring stations, characterized by a moderate to low level of contamination. However, the results show the difficulty of predicting this contaminant in those stations that present critical contamination episodes, such as ATE and HCH. In conclusion, the LSTM recurrent artificial neural networks with BNCV adapt more precisely to critical pollution episodes and have better predictability performance for this type of environmental data.

Statistical modeling approach for PM10 prediction before and during confinement by COVID-19 in South Lima, Perú

“…On the contrary, positive and direct correlations were calculated (r WS-PM 10 − anual(0.40526) ), especially for summer (r WS-PM 10 (0.55296) ) and autumn (r WS-PM 10 (0.56274) ). These values are higher than other studies reported in Lima 34 , indicating influence on PM 10 dispersion, resuspension and transport, including its decrease with the simultaneous diminution of wind 50 . The non-parametric regression produced a coefficient of determination R 2 = 0.182 , close to other studies on the same variable 13 (Fig.…”

“…Similarly, the Weather Research and Forecasting-Chem (WRF-Chem) model was applied to develop an operational forecast system for air quality in the Metropolitan Area of Lima and Callao (MALC) 12 . Air quality for PM 10 was also evaluated in other districts of Lima through the application of artificial neural networks (ANN), observing certain difficulties for its prediction in stations with critical pollution episodes 34 .…”

Statistical and Artificial Neural Networks Models for Electricity Consumption Forecasting in the Brazilian Industrial Sector

“…For future research, we can apply other univariate models, such as Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) [40,41], and bootstrap-based models, and develop a hierarchical time-series forecast strategy to compare with the classical structure applied in this study. Finally, another avenue for future work would be to study the multivariate models (such as vector autoregressive, Bayesian vector autoregressive, artificial neural networks models with multiple features in the input layer) and compare with the univariate approach.…”

Evaluation of College Students’ Classroom Learning Effect Based on the Neural Network Algorithm

“…is paper believes that the socalled learning evaluation is under the guidance of the national education policy, under the guidance of the education policy, based on the implementation requirements of specific teaching objectives, applying the theories and methods of systematic science and responding to the realization of the teaching objectives in various teaching and learning processes. To establish an objective evaluation standard system, measure the relevant data and data collection, display, and inspection and make a relatively objective value judgment [7,8]. Learning evaluation is a systematic investigation of teaching effects or all aspects of student development according to certain standards and value analysis and judgment based on the acquisition of sufficient data.…”