Against the backdrop of global warming, the increasing spatiotemporal variability in precipitation patterns has intensified the frequency and risk of dry-wet abrupt alternation (DWAA) events in semi-arid regions. This study investigates the Hailar River Basin in northern China (1980-2019) and develops the Soil Moisture Concentration Index (SMCI) using daily soil moisture (SM) data simulated by the VIC hydrological model. A high-resolution temporal framework is introduced to detect DWAA events and evaluate the impact of precipitation pattern variations on dry-wet transitions in the basin. The results indicate: (1) Annual precipitation in the basin has significantly increased (0.47 mm y(-1) in the south, P < 0.05), while precipitation intensity follows a gradient pattern, increasing in the upstream (3.65 mm d1 y1) and decreasing in the downstream (-2.34 mm y(-1)). Additionally, the number of dry days and short-duration, high-intensity precipitation events has risen; (2) Soil moisture (SM) data simulated by the VIC model effectively capture DWAA events, showing significantly higher | SMCI| values downstream than upstream (P < 0.05) and indicating more intense dry-wet transitions in the downstream region. Furthermore, 78 % of the area exhibits an increasing trend in |SMCI|(1980-2019), with dry-to-wet transition events occurring more frequently than wet-to-dry events. For instance, in 2013, the maximum coverage area reached 48 % in a single day; (3) The random forest model highlights the spatial heterogeneity of DWAA driving factors: upstream water yield is the dominant factor, whereas downstream variations are closely associated with precipitation intensity (R-2 = 0.76) and the frequency of heavy rainfall days. Permafrost degradation and land use changes further heighten hydrological sensitivity in the downstream region. This study offers a transferable methodological framework for understanding extreme hydrological events and reveals that the driving mechanisms of DWAA are spatially heterogeneous, shifting from being dominated by terrestrial factors in the headwaters to meteorological factors downstream-a finding with significant implications for water resource management in other large, heterogeneous semi-arid basins.

Climate change still adversely affects agriculture in the sub-Saharan Africa. There is need to strengthen early action to bolster livelihoods and food security. Most governments use pre- and post-harvest field surveys to capture statistics for National Food Balance Sheets (NFBS) key in food policy and economic planning. These surveys, though accurate, are costly, time consuming, and may not offer rapid yield estimates to support governments, emergency organizations, and related stakeholders to take advanced strategic decisions in the face of climate change. To help governments in Kenya (KEN), Zambia (ZMB), and Malawi (MWI) adopt digitally advanced maize yield forecasts, we developed a hybrid model based on the Regional Hydrologic Extremes Assessment System (RHEAS) and machine learning. The framework is set-up to use weather data (precipitation, temperature, and wind), simulations from RHEAS model (soil total moisture, soil temperature, solar radiation, surface temperature, net transpiration from vegetation, net evapotranspiration, and root zone soil moisture), simulations from DSSAT (leaf area index and water stress), and MODIS vegetation indices. Random Forest (RF) machine learning model emerged as the best hybrid setup for unit maize yield forecasts per administrative boundary scoring the lowest unbiased Root Mean Square Error (RMSE) of 0.16 MT/ha, 0.18 MT/ha, and 0.20 MT/ha in Malawi's Karonga district, Kenya's Homa Bay county, and Zambia's Senanga district respectively. According to relative RMSE, RF outperformed other hybrid models attaining the lowest score in all countries (ZMB: 25.96%, MWI: 28.97%, and KEN: 27.54%) followed by support vector machines (ZMB: 26.92%, MWI: 31.14%, and KEN: 29.50%), and linear regression (ZMB: 29.44%, MWI: 31.76%, and KEN: 47.00%). Lastly, the integration of VI and RHEAS information using hybrid models improved yield prediction. This information is useful for NFBS bulletins forecasts, design and certification of maize insurance contracts, and estimation of loss and damage in the advent of climate justice.