evidoria

← Back to browse

Good practice Imported

ESW4 — Metro Manila's KOICA-Funded AI Flood Forecasting and Early Warning Network

Philippines · Quezon City · See the Philippines profile · See the Quezon City profile

Evidence: Descriptive / self-reported Top 36% 67/100 · Ask Evidence Copilot about this practice

A $12.7m Korean-funded project has installed an AI-assisted flood forecasting system and warning centre for the Pasig-Marikina-Tullahan river basins, intended to serve roughly 21.4 million residents across Metro Manila, Bulacan, Cavite, Laguna and Rizal.

12.7 USD million
KOICA grant funding (2023-2025)
21.4 million residents
Population within the system's coverage area (as of inauguration)

Details

Maturity
Established
Promoter
DOST-PAGASA and Korea International Cooperation Agency (KOICA)
Period
2023-2026
Keywords
disaster risk reduction, meteorology, hydrology, climate resilience

Context

ESW4 (Enhancing Weather and Flood Forecasting and Warning System) is a $12.7 million grant project funded by the Korea International Cooperation Agency (KOICA) and implemented with the Philippine Atmospheric, Geophysical and Astronomical Services Administration (DOST-PAGASA), installing an integrated flood forecasting and early-warning system across flood-prone river basins in and around Metro Manila.

Activities

The project installed new hydrological observation and warning infrastructure plus dynamic, AI-assisted flood simulations built on high-resolution 3D spatial data and real-time dam/river monitoring; engineering design was completed in 2023, hardware installation ran through 2024-2025, and the Korean government and PAGASA inaugurated the Pasig-Marikina-Tullahan River Basin Flood Forecasting and Warning Center in Quezon City. The project also trains local government personnel to operate the new warning facilities.

Results

KOICA and PAGASA describe the intended beneficiary population as approximately 21.4 million residents of the National Capital Region and the provinces of Bulacan, Cavite, Laguna and Rizal; however, no independently verified figures on forecast lead-time gains, false-alarm rates, or actual flood-damage reduction have been published since the centre's inauguration, and the 21.4 million figure describes coverage-area population rather than a measured number of people who have received an accurate warning.

Implementation
Indicative cost
High (€500k–€5M)
Time to results
Long (> 3 years)
Staffing & skills
DOST-PAGASA operates the forecasting and warning centre, KOICA (Korea International Cooperation Agency) funded and co-implemented the project, Local government personnel are trained to operate the new warning facilities

Conditions for success

  • New hydrological observation and warning hardware paired with AI-assisted flood simulations using high-resolution 3D spatial data and real-time dam/river monitoring
  • Multi-year engineering design (completed 2023) preceded hardware installation (2024-2025)

Common failure modes

  • No independently verified figures on forecast lead-time gains, false-alarm rates, or actual flood-damage reduction have been published since inauguration
  • The 21.4 million figure is coverage-area population, not a measured number of people who received an accurate warning

Where it fits

Governance type
national government agency with bilateral donor co-implementation
Scale
regional (multi-province)
Income level
lower-middle-income

Commonly funded by

National / regional programmes

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Similar practices you may find useful