The need for accurate estimates of reference crop evapotranspiration (ETo) is important in irrigation planning and design, irrigation scheduling, reservoir management among other applications. ETo can be accurately determined using the internationally accepted FAO Penman–Monteith (FAO-56 PM) equation. However, this requires numerous observed data, including solar radiation, air temperature, relative humidity, and wind speed, which in most cases are unavailable, particularly in developing countries such as the Philippines. This study developed models based on Support Vector Machines (SVMs) and Extreme Learning Machines (ELMs) for the estimation of daily ETo using different input combinations of meteorological data in Region IV-A, Philippines. The performance of machine learning models was compared with the different established alternative empirical models for ETo. The results show that the SVM and ELM models, with at least T_max, T_min, and R_s as inputs, provide the best daily ETo estimates. The accuracy of machine learning models was also found to be superior compared to the empirical models given with same input requirements. In general, SVM and ELM models showed similar modeling performance, although the former showed lower run time than the latter.

Understanding the spatiotemporal distribution of extreme rainfall and meteorological drought on a watershed scale could be beneficial for local management of any water resources system that supports dam operation and river conservation. This study considered the watershed of Angat as a case, given its economic importance in the Philippines. A series of homogeneity tests were initially conducted on each rainfall dataset from monitoring stations in and near the watershed, followed by trend analysis to determine the rate and direction of change in the annual and seasonal rainfall extreme indices in terms of intensity, duration, and frequency. Three indices, using the rainfall deviation method (%DEV), percent of normal rainfall index (PNRI), and Standardized Precipitation Index (SPI), were also used to identify meteorological drought events. Generally, rainfall in the watershed has an increasing annual PCPTOT (4–32 mm/year), with increasing frequency and intensity in heavy rainfall and wet days. A significant increasing trend (α = 5%) in the seasonal PCPTOT (7–65 mm/year) and R10mm (1.7–10.0 days/decade) was particularly observed in all stations during the Amihan Monsoon Season (Dec–Feb). The observed increasing rainfall intensity and frequency, if it continues in the future, could have an implication both for the water resources operation to satisfy the multiple objectives of Angat Reservoir and for the flood operation that prevents damage in the downstream areas. The effect of each ENSO (El Niño- Southern Oscillation) phase on the rainfall is unique in magnitude, intensity, and duration. The seasonal reversal of the ENSO in the extreme rainfall and meteorological drought signals in Angat Watershed was also evident. The identified meteorological drought events in the watershed based on SPI-12 persisted up to 12–33 months, could reduce more than 60% (PNRI < 40%) of the normal rainfall. Insights from the study have implications for the hydrology of the watershed that should be considered for the water resources management of the Angat Reservoir.

The rising global temperature and changing climate patterns have increased the frequency and intensity of extreme heat events, droughts, and heavy precipitation, significantly affecting agriculture, water resources, and ecosystems. Solar radiation management (SRM) has been proposed as a geoengineering strategy to mitigate these effects by reducing incoming solar radiation. This study evaluated future trends and variability in rainfall and temperature extremes in the Philippines under GeoMIP (G6Solar and G6Sulfur) and ScenarioMIP (SSP2-4.5 and SSP5-8.5) projections. Using five General Circulation Models (GCMs) and a suite of 10 climate indices recommended by the Expert Team on Climate Change Detection and Indices (ETCCDI), changes in extreme precipitation and temperature across different climate zones in the Philippines were assessed. Climate projections for the future (2041–2070) scenario were analyzed using bias correction, downscaling, and spatial interpolation techniques. Trend analysis was evaluated using the Mann–Kendall test and Sen’s slope estimator, while variability was assessed through statistical methods. The results show widespread warming and increased extreme precipitation, but these trends vary significantly across regions. Non-uniform responses emerge across scenarios, with some northern regions experiencing decreases in specific precipitation indices despite the broader warming trend under SRM and non-SRM conditions. These findings provide critical insights into the potential impacts of SRM on future climate extremes in the Philippines and guidance on climate policy recommendations for decision-makers and stakeholders.

Hydroclimatic extremes are intensifying, escalating risks to ecosystems, infrastructure, and vulnerable communities. Rapid technological innovation and scientific discovery offer powerful tools to address these challenges, yet a gap remains between hydroclimate knowledge production and its use in decision‐making. Bridging this divide requires democratizing hydroclimate science through expanded participation in research design and implementation, as well as in the distribution of recognition, resources, and decision power. Democratizing science can foster outcomes that are (a) more credible, through transparency and integration of decision‐maker perspectives; (b) more just, through fair distribution of research opportunities, resources, recognition, and decision power; and (c) more resilient, by strengthening the capacity of communities and institutions to adapt, learn, and recover from climate pressures. Drawing on insights from the 2024 Global Energy and Water EXchanges (GEWEX) Early Career Researcher Workshop, which gathered participants from 19 countries across disciplines, we outline pathways toward more democratic hydroclimate science grounded in diverse participation and shared leadership. We highlight three priorities: building trust through co‐production, improving the usability of hydroclimate information, and promoting responsible research and innovation in emerging technologies. Case studies illustrate how early‐ and mid‐career researchers and practitioners are advancing these priorities and modeling practices that connect innovation with equity. Achieving lasting and effective change requires research and funding institutions to recognize and support collaborative leadership, and to value relevance and accountability alongside technical excellence. Strengthening such democratic frameworks can help ensure that hydroclimate science advances more just research practices and supports the resilience of the communities it serves.