Artificial Intelligence in Data Science: Evaluating Forecasting Models for Solar Energy in the Amazon Basin

Forecasting models employing machine learning (ML) and deep learning (DL) have become fundamental for assessing the technical feasibility of renewable energy systems. Among these, solar energy stands out as a renewable energy option, particularly relevant for supporting the preservation of the Amazo...

Full description

Saved in:
Bibliographic Details
Main Authors: Andre Luis Ferreira Marques, Ricardo Sbragio, Pedro Luiz Pizzigatti Correa, Marcelo Ramos Martins
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11080416/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849304218580549632
author Andre Luis Ferreira Marques
Ricardo Sbragio
Pedro Luiz Pizzigatti Correa
Marcelo Ramos Martins
author_facet Andre Luis Ferreira Marques
Ricardo Sbragio
Pedro Luiz Pizzigatti Correa
Marcelo Ramos Martins
author_sort Andre Luis Ferreira Marques
collection DOAJ
description Forecasting models employing machine learning (ML) and deep learning (DL) have become fundamental for assessing the technical feasibility of renewable energy systems. Among these, solar energy stands out as a renewable energy option, particularly relevant for supporting the preservation of the Amazon rainforest. This study introduces a novel approach using ML and DL methods—integrated with Universal Kriging and Holt-Winters (time series) models — to forecast solar irradiance (kWh/m2) in cities across the state of Amazonas. The analysis is grounded in the Data Science cycle, with input data sourced from both ground stations and satellite products. Forecasting performance was evaluated for short-term horizons (one to three days ahead) across three representative cities. The hybrid SARIMAX-CNN-LSTM, SARIMAX-CNN-Transformer, and SARIMAX-TCN models achieved MAPE values ranging from 18.1% to 26.6% for the different forecast horizons and cities. These results are consistent with existing literature and reinforce the suitability of advanced ML/DL approaches for solar energy forecasting in highly variable and challenging environments such as the Amazon Basin.
format Article
id doaj-art-a67386dbb64b4501aed416b94e97f8e6
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a67386dbb64b4501aed416b94e97f8e62025-08-20T03:55:48ZengIEEEIEEE Access2169-35362025-01-011312506612507910.1109/ACCESS.2025.358927511080416Artificial Intelligence in Data Science: Evaluating Forecasting Models for Solar Energy in the Amazon BasinAndre Luis Ferreira Marques0https://orcid.org/0000-0003-4110-9398Ricardo Sbragio1Pedro Luiz Pizzigatti Correa2https://orcid.org/0000-0002-8743-4244Marcelo Ramos Martins3Computer Engineering Department, BigData Lab C216, Polytechnic School of the University of São Paulo, São Paulo, BrazilNaval Architecture and Ocean Engineering Department, Laboratory of Analysis, Evaluation and Risk Management (LabRisco), Polytechnic School of the University of São Paulo, São Paulo, BrazilComputer Engineering Department, BigData Lab C216, Polytechnic School of the University of São Paulo, São Paulo, BrazilNaval Architecture and Ocean Engineering Department, Laboratory of Analysis, Evaluation and Risk Management (LabRisco), Polytechnic School of the University of São Paulo, São Paulo, BrazilForecasting models employing machine learning (ML) and deep learning (DL) have become fundamental for assessing the technical feasibility of renewable energy systems. Among these, solar energy stands out as a renewable energy option, particularly relevant for supporting the preservation of the Amazon rainforest. This study introduces a novel approach using ML and DL methods—integrated with Universal Kriging and Holt-Winters (time series) models — to forecast solar irradiance (kWh/m2) in cities across the state of Amazonas. The analysis is grounded in the Data Science cycle, with input data sourced from both ground stations and satellite products. Forecasting performance was evaluated for short-term horizons (one to three days ahead) across three representative cities. The hybrid SARIMAX-CNN-LSTM, SARIMAX-CNN-Transformer, and SARIMAX-TCN models achieved MAPE values ranging from 18.1% to 26.6% for the different forecast horizons and cities. These results are consistent with existing literature and reinforce the suitability of advanced ML/DL approaches for solar energy forecasting in highly variable and challenging environments such as the Amazon Basin.https://ieeexplore.ieee.org/document/11080416/Deep learninglong short-term memorymulti-layer perceptrondata scienceAmazon Basinsolar energy
spellingShingle Andre Luis Ferreira Marques
Ricardo Sbragio
Pedro Luiz Pizzigatti Correa
Marcelo Ramos Martins
Artificial Intelligence in Data Science: Evaluating Forecasting Models for Solar Energy in the Amazon Basin
IEEE Access
Deep learning
long short-term memory
multi-layer perceptron
data science
Amazon Basin
solar energy
title Artificial Intelligence in Data Science: Evaluating Forecasting Models for Solar Energy in the Amazon Basin
title_full Artificial Intelligence in Data Science: Evaluating Forecasting Models for Solar Energy in the Amazon Basin
title_fullStr Artificial Intelligence in Data Science: Evaluating Forecasting Models for Solar Energy in the Amazon Basin
title_full_unstemmed Artificial Intelligence in Data Science: Evaluating Forecasting Models for Solar Energy in the Amazon Basin
title_short Artificial Intelligence in Data Science: Evaluating Forecasting Models for Solar Energy in the Amazon Basin
title_sort artificial intelligence in data science evaluating forecasting models for solar energy in the amazon basin
topic Deep learning
long short-term memory
multi-layer perceptron
data science
Amazon Basin
solar energy
url https://ieeexplore.ieee.org/document/11080416/
work_keys_str_mv AT andreluisferreiramarques artificialintelligenceindatascienceevaluatingforecastingmodelsforsolarenergyintheamazonbasin
AT ricardosbragio artificialintelligenceindatascienceevaluatingforecastingmodelsforsolarenergyintheamazonbasin
AT pedroluizpizzigatticorrea artificialintelligenceindatascienceevaluatingforecastingmodelsforsolarenergyintheamazonbasin
AT marceloramosmartins artificialintelligenceindatascienceevaluatingforecastingmodelsforsolarenergyintheamazonbasin