This paper examines how machine learning (ML) techniques can enhance the Water Evaluation and Planning (WEAP) model for surface water distribution strategies in the context of climate variability. Recent advancements in ML, General Circulation Models (GCMs), satellite data, and climate projections offer new opportunities for improved water resource management. However, methodological challenges remain in integrating these techniques across scientific disciplines and translating theoretical research into practical applications. The paper evaluates the effectiveness of the WEAP model in scenario planning while identifying uncertainties arising from dynamic socio-economic changes and climate variability. It demonstrates how ML enhances WEAP’s capabilities by improving forecasting accuracy, recognising hydrological patterns, and reducing measurement uncertainties. Furthermore, scenario-based modelling, powered by ML, offers sustainable water management solutions tailored to water-stressed regions facing increasing environmental and demand pressures. By synthesising insights from diverse research, this paper offers actionable recommendations for researchers, policymakers, and practitioners seeking to develop resilient water distribution systems in vulnerable regions.

A developing trend in stormwater treatment and management is the use of green technologies. Plant biofilters have been gaining increasing use in support of green technology objectives. This technical note reports on the development and preliminary testing of a laboratory-scale plant biofilter prototype for ammonia removal using a South African native plant species (Juncus effusus). The prototype design was based on a conceptual model for nitrogen fixation, plant uptake, bacterial nitrification and soil sorption. Additionally, a plug compartment was incorporated into the design to simulate plug flow as part of the conceptual model. Biofilter models with and without inoculated bacteria were compared. Ammonia reduction, nitrite and nitrate formation were observed. Results showed that the inoculated plant biofilter performed best, with an average of 61% reduction in ammonia within the filter compared to 15% in the normal plant biofilter. The incorporation of a plug compartment aided in slowing down the ammonia infiltration rate, increasing the retention time, and allowing for nitrification to occur.

The Berg River Dam is equipped with the first multi-level draw-off environmental flood release outlet in South Africa and can release flows up to about 200 m3/s. The outlet is controlled by a radial gate at the outlet end, and is protected by a vertical emergency gate near the inlet end. Commissioning tests of the emergency gate in 2008 found that large volumes of air were expelled, instead of the expected air entrainment into the air vent, designed to reduce expected negative pressures in the conduit during emergency gate closure. This paper describes the testing of a 1:14 physical model representing the outlet works of the Berg River Dam to determine the reasons for the unexpected release of air from the outlet work's air vent, as observed in the field during the commissioning tests of the emergency gate in the outlet conduit. Simulations of continuous gate closure on the as-built physical model of the Berg River Dam outlet showed predominant inflow of air into the air vent during emergency gate closure, with intermittent short duration high-speed air releases during the stages of emergency gate openings between 37% and 25% open. The problem was determined to be one of intermittent air blowback from the outlet conduit via the air vent during the latter stage, rather than continuous air release for all stages of the gate opening operation. The cause of the blowback was found to be the constriction of flow due to a reduction in the conduit cross-section at the radial gate chamber located at the downstream end of the outlet conduit. Key words: Berg River Dam, emergency bottom outlet gate, air blowback, constricted roof, high-headed outlets

Sand traps are essential for managing sedimentation in irrigation systems, ensuring the efficiency and longevity of water infrastructure. This study addresses the underperformance of the Lower Usuthu Smallholder Irrigation Project (LUSIP) sand trap in the Usuthu River basin, eSwatini, where sediment build-up disrupts its operational efficiency. Field investigations and advanced numerical modeling using ANSYS Fluent, the study evaluates the trapping and flushing efficiency of the sand trap. A fully coupled 3D numerical model simulates hydrodynamics and sediment transport, focusing on flow velocity and suspended sediment concentration distributions under both maximum design discharge and low-flow conditions. Field investigations revealed a trapping efficiency of 27% and a flushing efficiency of 36% during low-flow conditions, primarily due to turbulence and design limitations. Numerical simulations identified critical sediment deposition patterns and flow dynamics, leading to design recommendations. With the proposed modifications, the sand trap's trapping efficiency is projected to increase to 85%, while flushing efficiency is expected to reach 80% under low-flow conditions. This study introduces innovative modeling approaches to assess three-dimensional flow dynamics in distributed-sediment-excluder systems, offering actionable insights for optimizing sediment management in irrigation infrastructure. These findings contribute to sustainable agricultural development and water resource management, addressing challenges in semi-arid regions.

Ski-jump spillways redirect floodwater using a trajectory bucket to ensure the jet impinges the plunge pool at a predetermined impact location that avoids adverse loading on the dam foundation. While energy dissipation primarily occurs in the plunge pool, the high erosive power of a compact jet can induce significant scour damage to the pool bottom. To mitigate this, innovative trajectory bucket designs featuring splitter teeth or a central insert have been explored. A 1:25 scale model study was conducted to compare two trajectory bucket variations with a conventional design, assessing their impact on energy dissipation downstream of a ski-jump spillway. Both modified configurations outperformed the conventional design, with the splitter teeth design demonstrating superior performance in energy dissipation and reducing scour potential.

A 1:15 scale physical hydraulic model was designed and constructed to investigate the incipient failure conditions of large angular riprap. A total of 32 tests were performed on angular riprap dumped on steep bed slopes of 0.333 to 0.5, and against a steep side-bank slope of 0.4 in a wide trapezoidal channel. The critical movability number value defining the critical incipient failure conditions of angular riprap on steep bed slopes and steep side-bank slopes was determined to be 0.12 and 0.227, respectively. Based on the HEC-RAS 1-dimensional (1-D) steady-state flow analysis, it was identified that HEC-RAS overestimates the critical incipient failure movability number of the steep bed and steep side-bank riprap by a critical factor of 1.91 and 1.35, respectively. The applicability of the study’s findings is limited to prototype riprap D50 sizes of 0.57 m to 1.125 m, and a trapezoidal canal bottom-width to D50 ratio of 16:31 (Wbase: D50).