Model validation & governance

The evidence a model-validation team, the Bank of Ghana, the IFC and the World Bank asked for: a documented version and dataset registry, a hindcast against a real Ghanaian flood event, and a parameter sensitivity analysis. This is screening-grade validation — it demonstrates the hazard layer points at the right places and that no single financial assumption dominates; it is not a catastrophe-model back-test.

1 · Accra flood — in-sample design-coverage check (3 June 2015 Odaw/Korle disaster)

Read this honestly. This is an in-sample check: the flood layer's basins were defined using this same June-2015 event, so a high hit/spare rate confirms the model captures its design intent — it is not an out-of-sample skill score, and the raw counts below (12/12 and 6/6) are on a small hand-picked set. Genuine out-of-sample validation against an independent event (e.g. Kumasi 2021, Accra 2023) with a multi-threshold ROC, plus an independent third-party model review, is the step before regulatory reliance. Note this hindcast runs on the offline SEED geographic model — the coarse triage layer, not the LIVE FloodGuard / Sentinel-1 screen the tool uses by default. The satellite-observed flood check (section 1b) is the stronger, out-of-sample signal.

Does the flood layer flag the localities the documented June-2015 flood inundated, and spare the higher-ground areas it did not? A flood score ≥ 0.50 counts as "High+ flagged".

12/12Flooded localities flagged (in-sample coverage, not a skill score)

6/6Higher-ground controls spared (in-sample)

18Localities in the check (small sample)

Documented flooded — should flag

Locality	Flood score	Result
Kwame Nkrumah Circle	0.83	✓ flagged
Odawna	0.91	✓ flagged
Alajo	0.67	✓ flagged
Avenor	0.76	✓ flagged
Agbogbloshie	0.82	✓ flagged
Old Fadama	0.86	✓ flagged
Kaneshie	0.71	✓ flagged
Adabraka	0.87	✓ flagged
Nima	0.75	✓ flagged
Mamobi	0.73	✓ flagged
Korle Gonno	0.68	✓ flagged
Kasoa / Weija lowland	0.78	✓ flagged

Higher-ground control — should spare

Locality	Flood score	Result
East Legon	0.05	✓ spared
Cantonments	0.41	✓ spared
Airport Residential	0.41	✓ spared
Adenta	0.05	✓ spared
Legon (University)	0.05	✓ spared
Oyarifa	0.05	✓ spared

Sources: the 3 June 2015 Accra flood-and-fire (~269 mm in 3 days; the Kwame Nkrumah Circle GOIL explosion; AMA demolitions along the Odaw and at Old Fadama/Agbogbloshie). At screening resolution the flood layer reproduces the event's geography; calibration to a bank's recorded loss amounts is the next step.

1b · Observed vs modelled flood — the satellite check (Sentinel-1)

Beyond modelled susceptibility, a live screen queries Sentinel-1 C-band radar (Copernicus, which images through cloud) using UN-SPIDER change detection. Where the satellite actually recorded standing water on a parcel, the tool floors flood at High and flags "Sentinel-1 OBSERVED FLOOD on <date>" — measured reality, distinct from the odds, with the observation date. This is an out-of-sample, observed signal (the complement to the in-sample hindcast above): it does not depend on the seed model at all.

Verified end-to-end against the October 2023 Lower Volta / Akosombo dam-spill flood — the satellite footprint (≈16,000 ha) flags the inundated parcels, and a probe there returns the observed flood on 2023-10-22. Strongest for open-water / floodplain / riverine exposure; by radar physics it does not capture brief urban flash-flooding under rooftops, so an empty result in a dense city is a sensor limitation, not an all-clear. Live now for Greater Accra and the Lower Volta; nationwide backfill is in quality-controlled validation.

2 · Parameter sensitivity — which assumption matters?

Each finance constant varied ±20%; the table shows the % change in the demo book's total climate-driven Expected Credit Loss (ECL) uplift (base GHS 428,223), ranked by span. The base book is the synthetic 200-asset seed demo. The dominant lever is the forced-sale recovery — a well-understood collateral parameter — and no single knob produces a runaway result.

Constant	−20%	+20%	Span (impact)
Forced-sale recovery	+42.7%	-60.1%	102.8
Through-the-cycle base PD	-20.0%	+20.0%	40.0
AAL multiplier (global loss scale)	-12.5%	+13.9%	26.4
Capitalisation rate	+14.9%	-9.0%	23.9
Market repricing share of AAL	-10.7%	+11.7%	22.4
AAL convexity exponent	+10.2%	-8.0%	18.2
Downturn LGD floor	+2.8%	-3.0%	5.8
Uninsured share of damage	-2.1%	+2.1%	4.2

Acronyms: AAL = Average Annual Loss (expected yearly physical damage). ECL = Expected Credit Loss (PD × LGD × EAD). PD = probability of default · LGD = loss given default · EAD = exposure at default. Full definitions in the Knowledge Centre glossary.

3 · Return-period portfolio loss — the acute tail

Average annual loss understates a correlated catastrophe. Each hazard-prone region is modelled as an independent annual event (it fires with a probability rising with its acute-hazard severity and inflicts the simultaneous climate-LGD-weighted loss on its High+ assets); the portfolio loss distribution is the exact convolution of those events — deterministic, no Monte Carlo. Demo book: expected acute annual GHS 2.35M, worst single region Greater Accra (GHS 11.62M).

Return period	Annual exceedance	Portfolio loss
1-in-5	20.0%	GHS 2.00M
1-in-10	10.0%	GHS 11.62M
1-in-25	4.0%	GHS 12.84M
1-in-50	2.0%	GHS 13.09M
1-in-100	1.0%	GHS 13.59M
1-in-200	0.5%	GHS 13.86M

An indicative screening tail, not a full catastrophe model — it does not resolve event footprints or sub-regional correlation, and the regional event probabilities are stated screening assumptions. It gives a risk committee the 1-in-50 / 1-in-100 view a supervisor's stress test and a reinsurer both expect.

4 · Model governance

Version 2.12.0 (2026-08-11) · Owner / developer: Dr. Minka Aduse-Poku (PortfolioCheck methodology owner and developer) · the active parameter set is stamped on every report and return, each return carries a SHA-256 submission fingerprint, and the SEED engine is deterministic and stdlib-only, so any seed result re-runs bit-for-bit. A LIVE screen additionally records the source, resolution and observation date of each engine response (FloodGuard, SafeGround, Sentinel-1), so a live result is reconstructable from its logged inputs.

Independent validation (three lines of defence). Independent third-party model validation: NOT YET COMMISSIONED — recommended (and required for regulatory reliance) before any bank files on this tool. Development and validation must be segregated before a bank relies on the tool for a regulatory filing — commissioning that review is a stated pre-go-live step, not an afterthought.

Hazard & data sources (with vintage)

Layer	Source	Vintage
Flood / surface water	FloodGuard susceptibility grid · MERIT Hydro · JRC Global Surface Water · SafeGround constraints · Sentinel-1 observed-event extents	2021–2026
Coastal reference	OpenStreetMap coastline snapshot · ESA WorldCover 2021 land/water QA · Copernicus DEM elevation	2021 / snapshot 2026-07-27
Coastal change	Dated shoreline observations where available · Ghana sector literature registry · Ghana Hydrological Authority project reports	2008–2025 / registry 2026-07-27
Coastal sea level	IPCC AR6 scenario increments · PSMSL Takoradi station 331 retained with quality warning and excluded from trend fitting	AR6 / PSMSL 1929–2012
Heat	ERA5 hot-season apparent maximum and durable seasonal change · latitude + urban-heat-island + highland cooling in SEED mode	ERA5 through 2024
Riparian	SafeGround mapped watercourse proximity · continuous major-river polyline network (Volta system, Pra, Ankobra, Tano, Densu…) with point-to-segment distance in SEED mode	runtime / SEED
Land / protected	SafeGround protected-area, contamination and galamsey checks · Ramsar/protected anchors in SEED mode	runtime / SEED
Drought / water stress	NASA POWER rainfall climatology · FloodGuard rainfall deficit · Sentinel NDVI/VCI crop stress · aridity geography (savanna north + SE coastal dry belt) in SEED mode	runtime through 2026
Scenarios	IPCC AR6 SSP + NGFS (mapped) · World Bank Climate Knowledge Portal	AR6 / 2024
Damage basis	JRC Africa flood depth-damage curve (Huizinga et al. 2017) · First Street / UNDRR AAL tiers	2017 / 2025
Agricultural governance	Canonical source-to-variable, quality, minimum-input and validation register in core/agri_governance.py	2026-07-31
Agricultural calibration candidates	Ghana MoFA SRID yields/production · FAO WaPOR v3 · CHIRPS v3 · ISRIC SoilGrids 2.0 · FAO AquaCrop	Not yet used in scoring; registered 2026-07-31
Bank loss-data schema	PortfolioCheck LOSS-1.0: event, exposure, physical/production loss, insurance, credit outcome and evidence lineage fields	2026-07-31

Current version

Version	Date	What changed in this version
2.12.0	2026-10-03	Supervisor financed-emissions & transition roll-up — Phase 3b (completes the ESG extension). A Bank-of-Ghana system-wide view (GET /supervisor/financed + .csv, linked from the supervisory console) that rolls every bank's PCAF financed emissions and NGFS transition exposure up across the sector on the SAME engines: total system financed emissions (Scope 3 Cat. 15), the system Green Asset Ratio, the share of financed emissions in carbon-intensive segments, a sector financed-emissions pathway to 2050 under the four NGFS scenarios with the 1.5°C target overlaid, the sector transition carbon-cost (VaR) by horizon, regional financed-emission concentration (Herfindahl), a bank league table ranked on financed emissions / intensity / GAR / 1.5°C alignment (click to drill in), and the least-1.5°C-aligned banks. Because every bank runs the identical PCAF/NGFS method the figures are directly comparable — the macroprudential transition view the Directive and IFRS S2 target but no single bank can see. Cached + warmed like the physical console. New core/supervisor.financed_system_view / render_supervisor_financed / financed_system_rows; 2 new tests. All figures synthetic/illustrative, configurable, not audited.

Limitations (declared). This is a screening hindcast at locality resolution, not a parcel-level depth-damage back-test; financial constants are illustrative until calibrated to a bank's loss data; the model does not yet observe construction quality or insurance status unless recorded per asset; and an independent third-party technical review is recommended before regulatory reliance. The gap register on every board report lists what remains and who must close it.

PortfolioCheck methodology · Dr. Minka Aduse-Poku · PortfolioCheck v2.12.0 (2026-08-11) · Validation is screening-grade — it feeds, and does not replace, a bank's IFRS 9 / PD-LGD model validation.