The exact text we saved

This is the version exactly as it was saved, character for character. The SHA-256 hash below is a 64-character code worked out from that text. Run the same text through SHA-256 and you get the same code; change a single letter and the code comes out completely different. Each version also stores the previous version’s hash, which chains them together so no version can be swapped out quietly.

TRUVACE RECORD VERSION
record: TRV-2026-2565
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-11-12T07:55:08.786521Z
status: published
lens: g_space
sector: climate
headline: Object‐based deep learning for probabilistic convective‐core nowcasting from satellite data
dek: Abstract Flash flooding from intense rainfall causes major damage and loss of life across Africa, particularly in the Sahel, where rainfall is dominated by mesoscale convective systems. Convective cores, which represent regions of intense convective activity, evolve rapidly, limiting short‐term predictability, especially in data‐sparse regions where numerical weather prediction models face substantial uncertainty in convective initiation, evolution, and organisation. This study presents an object‐based deep‐lear…
gain_title: In a model evaluation for the western Sahel, a transformer called NCAST made skilful probabilistic forecasts of intense storm cores one, three and six hours ahead, beating persistence and an operational conditional-climatology benchmark.
problem_title: (none)
trace_subject: (none)
gain_reading: In a model evaluation for the western Sahel, a transformer called NCAST made skilful probabilistic forecasts of intense storm cores one, three and six hours ahead, beating persistence and an operational conditional-climatology benchmark.
gain_evidence: Evaluation against persistence and an operational conditional‐climatology benchmark demonstrates skilful forecasts at one‐, three‐, and six‐hour lead times
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers built a deep-learning system called NCAST that forecasts where intense convective cores, the most violent parts of Sahel rainstorms, will occur. It uses infrared images from the Meteosat Second Generation geostationary satellite and produces gridded probabilities for the western Sahel.

Flash flooding from intense rainfall causes major damage and loss of life across Africa, and weather models struggle in data-sparse regions to predict when storms start, evolve and organise. Short-range forecasts from satellite data could help fill that gap, though the work reports benchmark skill rather than flood outcomes.

Explainable AI analysis on a single-location version indicated that predictions rely on physically meaningful factors: how close, how large and how intense nearby cores are. Ablation tests showed self-attention contributed most to skill, with temporal information mattering more at longer lead times.
limitation: 
tag: Evidence-backed gain
key_points: Convective cores were identified from Meteosat Second Generation infrared imagery using a two-dimensional wavelet transform at mesoscale spatial scales. | A single-location demonstration used attributes of nearby cores to predict local core occurrence up to six hours ahead. | The full NCAST model is a spatio-temporal transformer that models the evolution and interactions of convective-core populations across the western Sahel. | Ablation experiments found self-attention contributed most strongly to forecast skill. | Temporal information became more important at longer lead times. | Skill was assessed against persistence and an operational conditional-climatology benchmark at one-, three- and six-hour lead times using several probabilistic and spatial verification metrics.
rundown: The Sahel's rainfall is dominated by mesoscale convective systems, whose cores change quickly. That limits short-term predictability, particularly where observations are sparse and numerical weather prediction models carry substantial uncertainty about storm initiation, evolution and organisation.

The study took an object-based approach: instead of predicting raw pixels, it detects convective cores as objects and models how their populations evolve and interact. It first tested the idea at one location, then scaled it to a gridded probabilistic forecast for the western Sahel.

Explainable AI analysis suggested the single-location predictions were driven by core proximity, size and intensity. Ablation experiments showed self-attention was the largest contributor to skill, and the authors conclude that object-based learning has potential for reliable short-range nowcasts in data-sparse environments.
sources:
- peer_reviewed | Quarterly Journal of the Royal Meteorological Society | https://doi.org/10.1002/qj.70303 | 2026-09-06
prev: 0000000000000000000000000000000000000000000000000000000000000000

SHA-256 hash

67ebdd1503f5038a07a89ba8d544270075b7c2b31e5ca9d42047f9ed592f0153

Previous version’s hash

0000000000000000000000000000000000000000000000000000000000000000