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-2026-2597
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-11-12T08:00:13.196724Z
status: published
lens: p_space
sector: climate
headline: Advancing climate resilience through artificial intelligence: A comprehensive review across urban and climate-sensitive sectors in Morocco
dek: Climate change poses significant challenges to Morocco, which is increasingly affected by desertification, recurrent droughts, rising temperatures, and water scarcity. These impacts threaten climate-sensitive sectors such as agriculture, water resources, energy, urban planning, and environmental management, highlighting the urgent need for innovative and data-driven resilience strategies. In this context, artificial intelligence has emerged as a promising tool for strengthening prediction, planning, risk managem…
gain_title: (none)
problem_title: A review of 80 publications from 2020–2025 found that Morocco's climate-resilience AI research is limited by sparse ground observations, restricted institutional data, limited spatial transfer testing and minimal explainable AI, constraining reproducibility and operational uptake.
trace_subject: (none)
gain_reading: (none)
gain_evidence: (none)
problem_reading: A review of 80 publications from 2020–2025 found that Morocco's climate-resilience AI research is limited by sparse ground observations, restricted institutional data, limited spatial transfer testing and minimal explainable AI, constraining reproducibility and operational uptake.
problem_evidence: sparse ground observations, restricted institutional data, resolution mismatch, limited spatial transfer testing, and minimal use of explainable AI constrained reproducibility and operational uptake
quick_read: A review of 80 eligible publications from 2020–2025 mapped how AI, machine learning and deep learning have been applied to climate resilience in Morocco across seven climate-sensitive sectors. Searches covered Google Scholar, IEEE Xplore, ScienceDirect and SpringerLink.

Research activity rose markedly after 2022, concentrated in agriculture, water resources and climate-risk applications. Morocco faces desertification, recurrent droughts, rising temperatures and water scarcity, which threaten agriculture, water, energy, urban planning and environmental management.

The review found that data and deployment gaps limited how far the work could be reproduced or put into operation. Most applications supported adaptation, while mitigation remained less developed.
limitation: The review found that sparse ground data, limited spatial transfer testing and minimal explainable AI constrained how reproducible and deployable the reviewed AI applications were.
tag: Evidence-backed problem
key_points: The review analysed 80 eligible publications from 2020–2025 on AI for climate resilience in Morocco. | Research activity increased markedly after 2022, especially in agriculture, water resources and climate-risk applications. | Tree-based ensembles were prevalent for heterogeneous tabular and geospatial data. | Neural models were used mainly for imagery and time-series forecasting. | Public satellite and reanalysis products enabled broad coverage of the country. | Sparse ground observations, restricted institutional data and resolution mismatch were among the constraints identified. | Most applications supported adaptation, while mitigation remained less developed.
rundown: The authors searched four databases and analysed each of the 80 eligible publications by sector, model family, dataset and access type, geographic scale, evaluation metric and stated or implicit research gap. The review covers seven climate-sensitive sectors.

Model choice followed data type: tree-based ensembles dominated for heterogeneous tabular and geospatial data, while neural models were used mainly for imagery and time-series forecasting. Public satellite and reanalysis products gave broad coverage.

Constraints included sparse ground observations, restricted institutional data, resolution mismatch, limited spatial transfer testing and minimal use of explainable AI. These limited reproducibility and operational uptake.

The authors present the Morocco-specific cross-sector synthesis as an evidence-based roadmap for reproducible, locally generalisable and trustworthy climate-AI systems, extending narrower domain reviews.
sources:
- peer_reviewed | City and Environment Interactions | https://doi.org/10.1016/j.cacint.2026.100461 | 2026-08-01
prev: 0000000000000000000000000000000000000000000000000000000000000000

SHA-256 hash

f990eef39035dc4793cafe466f62c9139666b0d8dd2fba2339c1ff600887fc09

Previous version’s hash

0000000000000000000000000000000000000000000000000000000000000000