Background: This paper explores strategies to enhance North-South collaboration to foster multi- and trans-disciplinary research in disaster risk reduction (DRR) and crisis management, emphasizing the role of open science, Artificial Intelligence (AI) and geoinformatics in developing a resilient and proactive approach to these challenges, as well as drawing on lessons learned from the COVID-19 pandemic, the paper highlights how collaboration and data sharing can enhance preparedness, response, and recovery in future crises. Methods: The study uses a mixed approach to gather and analyze information. Qualitative methods focus on gathering descriptive data through engaging with experts and a structured review. By investigating literature, a comprehensive strategic framework for minimizing disaster risk, and for crisis management, is developed to provide adequate guidance to policymakers on implementation strategies and the application of how to build the human, institutional, and technological capacity required for effective disaster and crisis management (DCM). The events were used to engage with experts to provide recommendations and opportunities to enhance crisis response, capacity development and policy. Findings:>By presenting a comprehensive framework that bridges theoretical knowledge with practical application, our findings indicate that governments must address the challenges of DCM to minimize losses. The practices surrounding disaster recovery can provide opportunities for policymakers to reassess priorities and redirect resources toward building sustainable communities. Originality: There is no strategic framework that provides adequate guidance to policymakers on implementation strategies or the application of how to build the human, institutional and technological capacity required for effective DCM. This article develops a Decision Support Framework for DCM. We outline how open science promotes cross-disciplinary collaboration and the sharing of knowledge, while geoinformatics, AI enable real-time data analysis that supports proactive disaster preparedness, response, and recovery. This paper encompasses a strategic, comprehensive, capacity-building framework for achieving sustainable strengthening of North-South collaboration. Furthermore, it presents how to design the most efficient data policies in times of crisis and how we can use these tools to improve North-South cooperation in Africa’s DCM. Finally, it highlights challenges of implementation and presents solutions and opportunities for Africa.

Federated Learning (FL) represents a promising paradigm for collaborative model training across numerous devices, preserving data locality and offering potential privacy benefits for industries such as finance, healthcare, and Internet of Things (IoT). Nonetheless, real-world deployments of FL encounter challenges arising from dynamic and diverse environments, which adversely affect training speed and model convergence. To address these issues, this paper introduces FedDCS, an adaptive federated learning framework that effectively manages resources during training through two primary innovations. First, it establishes a reliable method for predicting client training durations, estimating completion times while filtering noise and detecting performance variations. Second, it implements a two-stage adaptive waiting strategy that dynamically determines the optimal timing and selection of client batches for aggregation, thereby balancing collection efficiency with model accuracy. This approach optimizes the trade-off between efficiency and accuracy in heterogeneous settings. Extensive evaluations on datasets such as Fashion-MNIST and CIFAR-10/100, incorporating simulated device and data heterogeneity, demonstrate that FedDCS consistently achieves superior time efficiency and higher global model accuracy compared to state-of-the-art (e.g., synchronous, asynchronous, and semi-asynchronous) baselines. Its robustness and versatility render it effective across various complex and heterogeneous environments.