Deep Learning for Anomaly Detection in Spatio- Temporal Maharashtra Weather Data: A Novel Approach with Integrated Data Cleaning Techniques
Keywords:
climate, deep learning, LSTM Autoencoders, spatio-temporalAbstract
Maharashtra, located in the western part of India, experiences diverse climatic conditions owing to its vast geographical expanse. Seasonal patterns, such as the monsoon rains and dry summers, significantly impact the weather dynamics. This research includes primary data of Maharashtra State Monthly Dataset spanning from 2001 to 2022. Central to our approach is the integration of the expectation maximization optimization technique for data cleaning, addressing the challenges of noise and inconsistencies within the dataset. The primary objective is to enhance the robustness and accuracy of the weather data, laying a foundation for more reliable anomaly detection. Leveraging state-of-the-art algorithms such as One-Class SVM, Isolation Forest, LSTM Autoencoders, and Autoencoders, the research scrutinizes their efficacy in identifying anomalies within the complex temporal and spatial patterns inherent to Maharashtra's climate. The integrated data cleaning approach emerges as a novel aspect of this research, revealing its positive impact on refining the deep learning models' performance. Visualizations aid in intuitively understanding the detected anomalies and their implications for weather analysis. The results and discussion sections meticulously compare the outcomes of each algorithm, offering insights into their strengths and limitations. This approach provides a robust framework for anomaly detection in Maharashtra's weather data, enabling enhanced climate trend analysis, early detection of irregularities, and improved decision-making for disaster preparedness and resource allocation in the face of changing weather patterns.
Downloads
References
Jaseena, K. U., and Binsu C. Kovoor. "Deterministic weather forecasting models based on intelligent predictors: A survey." Journal of King Saud University-Computer and Information Sciences 34.6 (2022): 3393-3412.
Li, Zhenhui, and Shuchen Xiang. "A design of new wind power forecasting approach based on IVMD-WSA-IC-LSTM model." Journal of Engineering and Applied Science 70.1 (2023): 91.
Kumari, Sushma, et al. "Spatio-temporal analysis of air quality and its relationship with COVID-19 lockdown over Dublin." Remote Sensing Applications: Society and Environment 28 (2022): 100835.
Ma, Minbo, et al. "HiSTGNN: Hierarchical spatio-temporal graph neural network for weather forecasting." Information Sciences 648 (2023): 119580.
O'Donncha, Fearghal, et al. "A spatio-temporal LSTM model to forecast across multiple temporal and spatial scales." Ecological Informatics 69 (2022): 101687.
Sharma, Arun, Zhe Jiang, and Shashi Shekhar. "Spatiotemporal data mining: A Survey." arXiv preprint arXiv:2206.12753 (2022).
Wu, JT Chunrui, and Junfeng Tian. "Spatio-temporal outlier detection: A survey of methods." International Journal of Frontiers in Engineering Technology 2.1 (2020).
Amato, Federico, et al. "A novel framework for spatio-temporal prediction of environmental data using deep learning." Scientific reports 10.1 (2020): 22243.
Muthukumar, Pratyush, et al. "PM2. 5 Air Pollution Prediction through Deep Learning Using Multisource Meteorological, Wildfire, and Heat Data." Atmosphere 13.5 (2022): 822.
Ganjouri, Mahtab, et al. "Spatial‐temporal learning structure for short‐term load forecasting." IET Generation, Transmission & Distribution 17.2 (2023): 427-437.
Benmehaia, Amine M., Noureddine Merniz, and Amine Oulmane. "Spatiotemporal analysis of rainfed cereal yields across the eastern high plateaus of Algeria: an exploratory investigation of the effects of weather factors." Euro-Mediterranean Journal for Environmental Integration 5 (2020): 1-12.
Balti, Hanen, et al. "Spatio-temporal heterogeneous graph using multivariate earth observation time series: Application for drought forecasting." Computers & Geosciences 179 (2023): 105435.
Bentsen, Lars Ødegaard, et al. "Spatio-temporal wind speed forecasting using graph networks and novel Transformer architectures." Applied Energy 333 (2023): 120565.
Narkhede, Gaurav, et al. "Novel MIA-LSTM Deep Learning Hybrid Model with Data Preprocessing for Forecasting of PM2. 5." Algorithms 16.1 (2023): 52.
Goodge, Adam, et al. "Robustness of autoencoders for anomaly detection under adversarial impact." Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence. 2021.
Fan, Haoyi, Fengbin Zhang, and Zuoyong Li. "Anomalydae: Dual autoencoder for anomaly detection on attributed networks." ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020.
Wei, Yuanyuan, et al. "LSTM-autoencoder-based anomaly detection for indoor air quality time-series data." IEEE Sensors Journal 23.4 (2023): 3787-3800.
Saeed, Adnan, et al. "Hybrid bidirectional LSTM model for short-term wind speed interval prediction." IEEE Access 8 (2020): 182283-182294.
Erfani, Sarah M., et al. "High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning." Pattern Recognition 58 (2016): 121-134.
Xu, Hongzuo, et al. "Deep isolation forest for anomaly detection." IEEE Transactions on Knowledge and Data Engineering (2023).
Hudnurkar, Shilpa, et al. "Multivariate Time Series Forecasting of Rainfall Using Machine Learning." Artificial Intelligence of Things for Weather Forecasting and Climatic Behavioral Analysis, edited by Rajeev Kumar Gupta, et al., IGI Global, 2022, pp. 87-106. https://doi.org/10.4018/978-1-6684-3981-4.ch007
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
