This article explores the escalating impact of natural disasters, particularly droughts, in the Southern African Development Community (SADC), with a specific focus on Eswatini. Over the last century, approximately 63 million people in SADC countries have been affected by droughts, leading to challenges in agriculture, livestock losses, and severe food and water shortages. Despite being the smallest SADC nation, the Kingdom of Eswatini faces disproportionate consequences due to its susceptibility to climate variability, particularly drought. The inadequacy and unreliability of rainfall have resulted in a drastic reduction in food production, with maize, a staple crop, experiencing a 70% decline. This adverse trend, spanning three decades, has heightened the vulnerability of farmers to climatic shocks, hindering sustainable agricultural development and impeding poverty alleviation efforts. To address the growing threat of drought in the kingdom, a comprehensive approach is imperative, involving coordinated plans and the development of swift humanitarian relief strategies. This study utilized remote sensing technologies to monitor drought and assess its repercussions, evaluating the impact on agricultural production. Additionally, geospatial tools, including Open Route Service (ORS) and Near Neighbor Analysis algorithms, were employed to optimize humanitarian supply chain logistics. Results from the analysis, including Vegetation Health Index (VHI) fluctuations and drought severity mapping, reveal that 1990 was the year the kingdom was most severely hit by drought. This study also found that smallholder farmers practicing rainfed agriculture in vulnerable regions, such as the lower Middleveld and western Lowveld, suffered the severe socioeconomic consequences of agricultural drought, including income loss, food insecurity, and migration patterns. Through this integrated approach, decision makers can engage in targeted interventions, focusing on farming areas needing irrigation infrastructures or populated areas requiring a coordinated humanitarian response amidst climate variability.

In recent decades, there has been a growing interest in the application of GIS to community empowerment or new policy development through participatory design, information gathering and implementation. This study, therefore, aims to apply a multi-level participatory GIS (PGIS) framework to assess mobility needs and barriers in rural areas from different available transport modes. This assessment was applied to three sub-locations (Lusheya, Khaunga and Mahola) located in the sub-county of Mumias East, Kakamega, Kenya. The study brings two main contributions: (1) an overview of mobility needs and barriers in Sub-Saharan Africa (SSA) and (2) an introduction of a PGIS framework that integrates in-depth local knowledge of rural mobility needs and mobility barriers. This PGIS framework was applied to mobility issues based on three main dimensions: context, process and content. The context in the PGIS framework focuses on identifying the right stakeholders and putting on suitable structures for their training as well as the collection of data. The process considers the collection, analysis and visualization of rural mobility data. The content of the data collected are validated for accuracy in the form of maps and are evaluated for relevance by stakeholders. Local youths with GIS knowledge and digital tools were mobilized along with community people having a solid understanding of the local geographical contexts to collect geographically referenced data related to community resources, transport networks, and mobility barriers. The application of the multi-level PGIS framework has brought to the mainstream daily mobility challenges faced by rural communities in Sub-Saharan Africa. Community members, even those from remote areas, also have access to decision making, reversing the previous structure that strongly relied on often-irrelevant, top-down decision making.

Graph neural networks are increasingly used in rainfall–runoff modeling, with sub-watersheds as nodes and edges describing how they are linked. Edges are usually based on geographic distance, but in canal-regulated basins water follows canals and control structures rather than proximity. Whether a drainage-based graph outperforms a distance-based graph has rarely been tested with all other modeling choices held fixed. This study develops the Event-Based Spatio-Temporal Graph Convolutional Network (E-STGCN), which couples graph convolution with a recurrent neural network trained only on storm events, and uses it as a controlled experiment for this comparison. The framework was applied to five adjacent 12-digit Hydrologic Unit Code (HUC12) sub-watersheds of the Kissimmee River–Canal C-41A system in south-central Florida, using 111–252 storm events per extraction setting at 30-minute resolution from a decade of South Florida Water Management District DBHYDRO records. A full factorial design of 72 configurations varies the graph (drainage topology or k-nearest-neighbor proximity), the recurrent network (Long Short-Term Memory, Gated Recurrent Unit, or SimpleRNN), the loss function, and the event-extraction rule, each with five random seeds. The drainage-based graph outperformed the distance-based graph in 23 of 24 scenarios (combinations of event set, recurrent network, and loss function), with an average advantage about twice the variation between repeated runs. No configuration outperformed persistence, a forecast that holds discharge at its last observed value, so the results compare design choices rather than demonstrate forecasting skill. The drainage-based advantage was largest in the three basins with the lowest discharge variability, although five basins are too few to confirm this pattern. Models trained with a logarithmic loss failed, and the three recurrent networks performed similarly. Overall, in this canal-regulated network, which basins are linked in the graph affected accuracy more than the choice of recurrent network.

Attributing long-term vegetation change to climate is difficult in subtropical ecosystems, where temperature and precipitation act simultaneously, are confounded by abrupt disturbances, and where statewide averages can conceal offsetting associations. Here we apply a multi-method convergence-of-evidence framework to a sensor-harmonized 43-year record (1982–2024) of NOAA CDR NDVI, temperature, and precipitation across Florida, which spans cool temperate forests to warm subtropical wetlands. Modified Mann–Kendall tests with false-discovery-rate correction detected monotonic trends; pixel-level correlation, spatial-error regression, and lagged cross-correlation evaluated association strength, direction, and timing; Empirical Orthogonal Function decomposition of deseasonalized anomalies separated persistent climatic signals from episodic disturbance, with the leading mode (58.4% of variance) tracking latitudinal warming and a lower-order mode (PC3) tracking hurricane impacts. Florida warmed by +0.033 °C yr⁻¹, significant in 99.6% of land pixels, while precipitation showed no field-significant trend. The temperature–greenness association was positive across essentially the entire state, marginally stronger in the south; localized negative responses were confined to specific southern wetland and urban-fringe pixels rather than forming a systematic north–south reversal. The state-mean precipitation–NDVI correlation was negative at zero lag and reversed from r = −0.263 to r = +0.102 when incoming shortwave radiation was partialed out, consistent with cloud-associated light suppression rather than water limitation—a phenomenon we term the Water Paradox. SPI/SPEI–NDVI correlations were near zero, and Everglades water levels were largely decoupled from wetland greenness (r = 0.08, n.s.), indicating that inundation acts as a localized threshold modifier rather than a dominant suppressor. Climate–vegetation models for comparable high-rainfall subtropical systems may therefore need to account for spatially divergent temperature sensitivities and treat precipitation as an energy constraint rather than a uniform benefit.