This paper presents FORSEER (Forecasting by Selective Ensemble Estimation and Reconstruction), a novel methodology designed to address temperature forecasting under the challenges inherent to climate change. FORSEER integrates decomposition, forecasting, and ensemble methods within a modular framework. This methodology decomposes the time series into trend, seasonal, and residual components. Subsequently, multiple optimized forecast models are applied to each component. These component models are then carefully weighted and combined through an ensemble process to generate a final robust forecast. Experimental results demonstrate that FORSEER is an efficient computational forecasting methodology for complex climate time series. Furthermore, we show that FORSEER has an equivalent forecasting performance to the M4 competition champion SMYL method for temperature series. Besides, the proposed methodology has less computational complexity than SMYL, making it a more accessible and scalable option. FORSEER's modular architecture also allows flexibility when substituting techniques depending on the context of the problem, facilitating the parallel execution of independent tasks and resulting in a strategy adaptable to multiple contexts.
Climate change presents significant challenges due to the increasing frequency and intensity of extreme weather events. Mexico, with its diverse climate and geographic position, is particularly vulnerable, underscoring the need for robust strategies to predict atmospheric variables. This work presents TAE Predict (Time series Analysis and Ensemble-based Prediction with relevant feature selection) based on relevant feature selection and ensemble models of machine learning. Dimensionality in multivariate time series is reduced through Principal Component Analysis, ensuring interpretability and efficiency. Additionally, data remediation techniques improve data set quality. The ensemble combines Long Short-Term Memory neural networks, Random Forest regression, and Support Vector Machines, optimizing their contributions using heuristic algorithms such as Particle Swarm Optimization. Experimental results from meteorological time series in key Mexican cities demonstrate that the proposed strategy outperforms individual models in accuracy and robustness. This methodology provides a replicable framework for climate variable forecasting, delivering analytical tools that support decision-making in critical sectors, such as agriculture and water resource management. The findings highlight the potential of integrating modern techniques to address complex, high-dimensional problems. By combining advanced prediction models and feature selection strategies, this study advances the reliability of climate forecasts and contributes to the development of effective adaptation and mitigation measures in response to climate change challenges.
There is no recent comparison in the literature on the application of classical and machine learning methods for forecasting financial assets on the Mexican Stock Exchange (BMV). These methods divide the time series into three sections: training, validation, and testing. They predict future values using the training data and are evaluated in the validation phase using error metrics; once the lowest error is obtained, the best parameters and algorithms are used to predict values using the test section. This paper aims to find the most accurate regression algorithm to make predictions in the financial time series of the BMV. The regression methods compared include linear regression, neural networks, decision trees, and support vector regression. The study uses historical BMV asset price data to compare the accuracy of each of these algorithms.