A framework for controllable Pareto front learning with completed scalarization functions and its applications.

Pareto Front Learning (PFL) was recently introduced as an efficient method for approximating the entire Pareto front, the set of all optimal solutions to a Multi-Objective Optimization (MOO) problem. In the previous work, the mapping between a preference vector and a Pareto optimal solution is still ambiguous, rendering its results. This study demonstrates the convergence and completion aspects of solving MOO with pseudoconvex scalarization functions and combines them into Hypernetwork in order to offer a comprehensive framework for PFL, called Controllable Pareto Front Learning. Extensive experiments demonstrate that our approach is highly accurate and significantly less computationally expensive than prior methods in term of inference time.

The Mekong's future flows under multiple drivers: How climate change, hydropower developments and irrigation expansions drive hydrological changes.

The river flow regime and water resources are highly important for economic growths, flood security, and ecosystem dynamics in the Mekong basin - an important transboundary river basin in South East Asia. The river flow, although remains relatively unregulated, is expected to be increasingly perturbed by climate change and rapidly accelerating socioeconomic developments. Current understanding about hydrological changes under the combined impacts of these drivers, however, remains limited. This study presents projected hydrological changes caused by multiple drivers, namely climate change, large-scale hydropower developments, and irrigated land expansions by 2050s. We found that the future flow regime is highly susceptible to all considered drivers, shown by substantial changes in both annual and seasonal flow distribution. While hydropower developments exhibit limited impacts on annual total flows, climate change and irrigation expansions cause changes of +15% and -3% in annual flows, respectively. However, hydropower developments show the largest seasonal impacts characterized by higher dry season flows (up to +70%) and lower wet season flows (-15%). These strong seasonal impacts tend to outplay those of the other drivers, resulting in the overall hydrological change pattern of strong increases of the dry season flow (up to +160%); flow reduction in the first half of the wet season (up to -25%); and slight flow increase in the second half of the wet season (up to 40%). Furthermore, the cumulative impacts of all drivers cause substantial flow reductions during the early wet season (up to -25% in July), posing challenges for crop production and saltwater intrusion in the downstream Mekong Delta. Substantial flow changes and their consequences require careful considerations of future development activities, as well as timely adaptation to future changes.