A machine learning approach to analyse ozone concentration in metropolitan area of Lima, Peru

Carbo-Bustinza, Natalí; Belmonte, Marisol; Jimenez, Vasti; Montalban, Paula; Rivera, Magiory; Martínez, Fredi Gutiérrez; Mohamed, Mohamed Mehdi Hadi; Cruz, Alex Rubén Huamán De La; Costa, Kleyton da; López-Gonzales, Javier Linkolk

doi:10.1038/s41598-022-26575-3

“…These errors have been comparable to other STL decomposition studies that used root mean square error (RMSE: 6.8%) and mean absolute percentage error (MAPE: 10.49%) as benchmarks for forecast reliability for ozone [10]. This evaluation of tropospheric ozone explains its long-term and seasonal behavior with temporary ozone patterns [41], in accordance with what was demonstrated by Carbo-Bustinza [23] for the winter months in these geographic areas. This approach has presented high precision and strong performance that allows for preventing serious tropospheric ozone pollution events and optimizing the powers of the authorities and actors involved in decision making, especially at the urban level.…”

Section: Discussionsupporting

confidence: 86%

“…NPAR ARIMA In addition to the above, in the literature, Carbo-Bustinza [23] explored the correlations between ozone and meteorological variables and predicted ozone concentration for the same sites and winter periods selected in this study. They used models such as linear regression, support vector regression, decision trees, random forest, and multilayer perceptron and based their arguments on R 2 , MSE, and MAE.…”

Section: Parmentioning

confidence: 99%

“…Romero et al [22] evaluated the impact of meteorological variables on the ozone concentration and other pollutants present in the air through linear correlations made for data obtained between 2015 and 2018 at eight sampling stations in metropolitan Lima and reported that this pollutant increased with solar irradiation around 10:00 and 16:00 h, especially in spring, possibly caused by the interaction of primary NOx and hydrocarbon emissions from vehicle engines. Carbo-Bustinza et al [23] instead studied the behavior of ozone in winter using machine learning algorithms in four stations in the city of Lima and found the highest critical levels (165.80 µg/m 3 ) in the Ate district (ATE). However, we observed, in general, a drop in values in the cold season (O 3 < 100 µg/m 3 ), similar to another study [24].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Short-Term Forecasting of Ozone Concentration in Metropolitan Lima Using Hybrid Combinations of Time Series Models

Carbo-Bustinza,

Iftikhar,

Belmonte

et al. 2023

Applied Sciences

Self Cite

9

0

View full text Add to dashboard Cite

In the modern era, air pollution is one of the most harmful environmental issues on the local, regional, and global stages. Its negative impacts go far beyond ecosystems and the economy, harming human health and environmental sustainability. Given these facts, efficient and accurate modeling and forecasting for the concentration of ozone are vital. Thus, this study explores an in-depth analysis of forecasting the concentration of ozone by comparing many hybrid combinations of time series models. To this end, in the first phase, the hourly ozone time series is decomposed into three new sub-series, including the long-term trend, the seasonal trend, and the stochastic series, by applying the seasonal trend decomposition method. In the second phase, we forecast every sub-series with three popular time series models and all their combinations In the final phase, the results of each sub-series forecast are combined to achieve the results of the final forecast. The proposed hybrid time series forecasting models were applied to four Metropolitan Lima monitoring stations—ATE, Campo de Marte, San Borja, and Santa Anita—for the years 2017, 2018, and 2019 in the winter season. Thus, the combinations of the considered time series models generated 27 combinations for each sampling station. They demonstrated significant forecasts of the sample based on highly accurate and efficient descriptive, statistical, and graphic analysis tests, as a lower mean error occurred in the optimized forecast models compared to baseline models. The most effective hybrid models for the ATE, Campo de Marte, San Borja, and Santa Anita stations were identified based on their superior out-of-sample forecast results, as measured by RMSE (4.611, 3.637, 1.495, and 1.969), RMSPE (4.464, 11.846, 1.864, and 15.924), MAE (1.711, 2.356, 1.078, and 1.462), and MAPE (14.862, 20.441, 7.668, and 76.261) errors. These models significantly outperformed other models due to their lower error values. In addition, the best models are statistically significant (p < 0.05) and superior to the rest of the combination models. Furthermore, the final proposed models show significant performance with the least mean error, which is comparatively better than the considered baseline models. Finally, the authors also recommend using the proposed hybrid time series combination forecasting models to predict ozone concentrations in other districts of Lima and other parts of Peru.

show abstract

“…The results of the annual averages summarize the percentage of PM>NAAQS concentrations in the following order: (i) PM 10 : Ate (60–65%) > VMT (12–29.5%) > CDM (1.5–10%) (ii) PM 2.5 : Ate (20–24%) > VMT (4–8%) > CDM (0–0.6%). It is important to highlight that Ate is located on both sides of the country’s central highway, where vehicular traffic has increased 33 . Likewise, VMT has a sandy desert soil with a road saturated with public and private transportation that includes large cargo trucks 34 .…”

Section: Resultsmentioning

confidence: 99%

An exploratory analysis of PM$$_{2.5}$$/PM$$_{10}$$ ratio during spring 2016–2018 in Metropolitan Lima

Cabello-Torres,

Carbo-Bustinza,

Romero-Cabello

et al. 2024

Sci Rep

Self Cite

0

View full text Add to dashboard Cite

Aerosols (PM$$_{2.5}$$ 2.5 and PM$$_{10}$$ 10 ) represent one of the most critical pollutants due to their negative effects on human health. This research analyzed the relationship of PM and its PM$$_{2.5}$$ 2.5 /PM$$_{10}$$ 10 ratios with climatic variables in the austral spring (2016–2018) in Metropolitan Lima. Overall, there was an average PM$$_{2.5}$$ 2.5 /PM$$_{10}$$ 10 ratio of 0.33 with fluctuations from 0.30 to 0.35. However, there have also been high point values that reached ratios greater than one. This situation indicates a moderate condition of contamination by particulate matter with a predominance of coarse aerosols in spring, with an increasing trend over the years. The locations Ate and Villa Maria del Triunfo, especially Ate, presented poor quality conditions. Thursdays showed outstanding pollution peaks by PM$$_{10}$$ 10 , and a decrease is visible on Sundays. On the other hand, the PM$$_{2.5}$$ 2.5 showed a similar pattern every day, including Sundays. The maximum peaks occurred in the morning and night hours. The increase in anthropogenic emissions associated with the formation of secondary aerosols has been evident, being the case of the location Campo de Marte, the one that had a significant increase in ratios PM$$_{2.5}$$ 2.5 /PM$$_{10}$$ 10 , which confirms a greater intensity of secondary formations of carbonaceous particles from industrial oil sources, vehicle exhaust, as well as aerosols from metal smelting and biomass burning. There were negative correlations of the ratios with PM$$_{10}$$ 10 , temperature, wind speed, and direction, and positive correlations with PM$$_{2.5}$$ 2.5 and relative humidity. Contour lines were successfully developed that demonstrated the interaction of climate with PM$$_{2.5}$$ 2.5 /PM$$_{10}$$ 10 ratios. This will deepen the exploration of emission sources and modeling, which allows for optimizing air quality indices to control emissions and adequately manage air quality in Metropolitan Lima.

show abstract

“…Machine learning models such as deep learning and artificial neural networks can also be considered part of the current forecasting decompositioncombination technique. It can also be extended and applied to other approaches and datasets (for example, energy [1,3], air pollution [67][68][69][70], solid waste [71] and academic performance [72]).…”

Section: Conclusion and Future Work Directionsmentioning

confidence: 99%

Forecasting Day-Ahead Electricity Prices for the Italian Electricity Market Using a New Decomposition—Combination Technique

Iftikhar,

Turpo-Chaparro,

Canas Rodrigues

et al. 2023

Self Cite

View full text Add to dashboard Cite

Over the last 30 years, day-ahead electricity price forecasts have been critical to public and private decision-making. This importance has increased since the global wave of deregulation and liberalization in the energy sector at the end of the 1990s. Given these facts, this work presents a new decomposition–combination technique that employs several nonparametric regression methods and various time-series models to enhance the accuracy and efficiency of day-ahead electricity price forecasting. For this purpose, first, the time-series of the original electricity prices deals with the treatment of extreme values. Second, the filtered series of the electricity prices is decomposed into three new subseries, namely the long-term trend, a seasonal series, and a residual series, using two new proposed decomposition methods. Third, we forecast each subseries using different univariate and multivariate time-series models and all possible combinations. Finally, the individual forecasting models are combined directly to obtain the final one-day-ahead price forecast. The proposed decomposition–combination forecasting technique is applied to hourly spot electricity prices from the Italian electricity-market data from 1 January 2014 to 31 December 2019. Hence, four different accuracy mean errors—mean absolute error, mean squared absolute percent error, root mean squared error, and mean absolute percent error; a statistical test, the Diebold–Marino test; and graphical analysis—are determined to check the performance of the proposed decomposition–combination forecasting method. The experimental findings (mean errors, statistical test, and graphical analysis) show that the proposed forecasting method is effective and accurate in day-ahead electricity price forecasting. Additionally, our forecasting outcomes are comparable to those described in the literature and are regarded as standard benchmark models. Finally, the authors recommended that the proposed decomposition–combination forecasting technique in this research work be applied to other complicated energy market forecasting challenges.

show abstract

A machine learning approach to analyse ozone concentration in metropolitan area of Lima, Peru

Cited by 12 publications

References 45 publications

Short-Term Forecasting of Ozone Concentration in Metropolitan Lima Using Hybrid Combinations of Time Series Models

Short-Term Forecasting of Ozone Concentration in Metropolitan Lima Using Hybrid Combinations of Time Series Models

An exploratory analysis of PM$$_{2.5}$$/PM$$_{10}$$ ratio during spring 2016–2018 in Metropolitan Lima

Forecasting Day-Ahead Electricity Prices for the Italian Electricity Market Using a New Decomposition—Combination Technique

Contact Info

Product

Resources

About