An Efficient Task Implementation Modeling Framework with Multi-Stage Feature Selection and AutoML: A Case Study in Forest Fire Risk Prediction
-
Published:2024-08-29
Issue:17
Volume:16
Page:3190
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Su Ye12ORCID, Zhao Longlong1ORCID, Li Hongzhong1ORCID, Li Xiaoli1ORCID, Chen Jinsong13ORCID, Ge Yuankai4
Affiliation:
1. Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China 2. University of Chinese Academy of Sciences, Beijing 101407, China 3. Shenzhen Engineering Laboratory of Ocean Environmental Big Data Analysis and Application, Shenzhen 518055, China 4. The Eighth Engineering Co., Ltd., China Tiesiju Civil Engineering Group Co., Ltd., Hefei 230023, China
Abstract
As data science advances, automated machine learning (AutoML) gains attention for lowering barriers, saving time, and enhancing efficiency. However, with increasing data dimensionality, AutoML struggles with large-scale feature sets. Effective feature selection is crucial for efficient AutoML in multi-task applications. This study proposes an efficient modeling framework combining a multi-stage feature selection (MSFS) algorithm and AutoSklearn, a robust and efficient AutoML framework, to address high-dimensional data challenges. The MSFS algorithm includes three stages: mutual information gain (MIG), recursive feature elimination with cross-validation (RFECV), and a voting aggregation mechanism, ensuring comprehensive consideration of feature correlation, importance, and stability. Based on multi-source and time series remote sensing data, this study pioneers the application of AutoSklearn for forest fire risk prediction. Using this case study, we compare MSFS with five other feature selection (FS) algorithms, including three single FS algorithms and two hybrid FS algorithms. Results show that MSFS selects half of the original features (12/24), effectively handling collinearity (eliminating 11 out of 13 collinear feature groups) and increasing AutoSklearn’s success rate by 15%, outperforming two FS algorithms with the same number of features by 7% and 5%. Among the six FS algorithms and non-FS, MSFS demonstrates the highest prediction performance and stability with minimal variance (0.09%) across five evaluation metrics. MSFS efficiently filters redundant features, enhancing AutoSklearn’s operational efficiency and generalization ability in high-dimensional tasks. The MSFS–AutoSklearn framework significantly improves AutoML’s production efficiency and prediction accuracy, facilitating the efficient implementation of various real-world tasks and the wider application of AutoML.
Funder
National Key Research and Development Program of China National Natural Science Foundation of China Guangdong Basic and Applied Basic Research Foundation Undertaking National Science and Technology Major Project by Shenzhen Technology and Innovation Bureau Excellent Youth Innovation Foundation of the Shenzhen Institute of Advanced Technology of the Chinese Academy of Science
Reference60 articles.
1. Benchmark and Survey of Automated Machine Learning Frameworks;Huber;Artif. Intell. Res.,2021 2. Guyon, I., Chaabane, I., Escalante, H.J., Escalera, S., Jajetic, D., Lloyd, J.R., Macià, N., Ray, B., Romaszko, L., and Sebag, M. A brief Review of the ChaLearn AutoML Challenge: Any-time Any-dataset Learning without Human Intervention. Proceedings of the Workshop on Automatic Machine Learning. 3. Review of ML and AutoML Solutions to Forecast Time-Series Data;Alsharef;Arch. Comput. Methods Eng.,2022 4. Shen, Z., Zhang, Y., Wei, L., Zhao, H., and Yao, Q. (2018). Automated Machine Learning: From Principles to Practices. arXiv. 5. AutoML for Multi-Label Classification: Overview and Empirical Evaluation;Wever;IEEE Trans. Pattern Anal.,2021
|
|