Federated transfer learning for distributed drought stage prediction

被引：0

作者：

Muhammad Owais Raza ^{[1
]}

Aqsa Umar ^{[2
]}

Jawad Rasheed ^{[1
]}

Tunc Asuroglu ^{[3
]}

Shtwai Alsubai ^{[4
]}

机构：

[1] Istanbul Sabahattin Zaim University,Department of Computer Engineering

[2] Sindh Madressatul Islam University,Department of Computer Science

[3] Istanbul Nisantasi University,Department of Software Engineering

[4] Applied Science Private University,Applied Science Research Center

[5] Tampere University,Faculty of Medicine and Health Technology

[6] VTT Technical Research Centre of Finland,Department of Computer Science, College of Computer Engineering and Sciences

[7] Prince Sattam Bin Abdulaziz University,undefined

来源：

Discover Artificial Intelligence | / 5卷 / 1期

关键词：

Satellite images; Remote sensing; Transfer learning; Federated learning; Distributed learning;

D O I：

10.1007/s44163-025-00288-8

中图分类号：

学科分类号：

摘要：

Due to the uncertain nature of drought, it is one of the most menacing natural disasters. Drought modeling (Prediction, Detection, Forecasting, and Stage Prediction) is very essential for efficient policy making. But one of the key problems with drought modeling is the limited availability of centralized datasets. To address this problem, we are a novel proposing federated learning based transfer learning models for the prediction of drought stages. In this study, satellite image dataset was collected from the Tharparkar district (prone to drought) of Pakistan. We trained the dataset using traditional and federated learning approaches, comparing centralized ML models, pre-trained models, and their respective federated learning models (FL-ResNet, FL-DenseNet, FL-MobileNet). The development of these models is the novel aspect of the study specifically for the use case of drought stage prediction. Based on the final evaluation, FL-MobileNet achieved 82% precision while baseline MobileNet scored 68%. The results show the effectiveness of novelty (federated learning), that our proposed framework improves the performance of the drought stage classification task.

引用