The climate impacts of the coming decades are, in large part, already locked in. Mitigation remains essential, but it is no longer sufficient on its own. IEEE B-HTC 2027 places climate adaptation and resilience, not mitigation alone, at the centre of the technical programme.
Aligned with UN Sustainable Development Goal 13 (Climate Action) and its adaptation-focused targets — 13.1 (resilience and adaptive capacity) and 13.3 (early warning and capacity-building) — B-HTC 2027 seeks work that helps communities, infrastructure, and ecosystems anticipate, withstand, and recover from a climate that has already shifted.
We solicit original, unpublished full-length research papers reporting substantive technical contributions. Methods of interest include machine learning and deep learning, graph neural networks, generative and foundation models, reinforcement learning, physics-informed and hybrid modelling, computer vision and remote-sensing analytics, time-series forecasting, optimisation and operations research, simulation and digital twins, and federated and edge learning for distributed, low-connectivity settings.
Every submission must demonstrate methodological rigour, quantitative evaluation, and reproducibility sufficient for indexing in IEEE Xplore. We especially welcome work that is deployed or validated in context, that quantifies an adaptation outcome, and that advances open datasets, digital public goods, and reproducible tooling.
All deadlines are 23:59 Anywhere on Earth (AOE, UTC−12). Submission-cycle dates are proposed to standard IEEE norms and subject to Organising Committee ratification; the conference dates are fixed.
A single track, open to all authors from academia, industry, government, and civil society. IEEE two-column format, inclusive of all figures, tables, and references, reporting original, unpublished, and rigorously evaluated technical work. Papers targeting the Transform focus area must additionally include a technical artefact — conceptual framing alone is out of scope for that area.
Each paper is reviewed by at least three members of the Technical Program Committee. Reviews assess technical soundness and adaptation outcome as distinct axes: a paper must earn both. Submissions that assert impact without evidence, omit baselines or evaluation, or cannot substantiate a quantified adaptation outcome will not be competitive, regardless of topical relevance.
A clearly articulated, non-incremental technical contribution positioned against the current state of the art.
Appropriate, correctly applied methods, with assumptions, threats to validity, and limitations stated explicitly.
Results validated against baselines, benchmarks, or real-world data using appropriate metrics, with ablations, error and uncertainty analysis, and statistical treatment where relevant.
Sufficient detail — data, code, parameters, and settings — for independent reproduction; release of open artefacts is strongly encouraged.
A measured resilience or adaptive-capacity gain, scored as a distinct axis from technical soundness.
Across all focus areas, submissions must demonstrate technical depth, sound methodology, and quantitative evaluation. Topical fit alone is not sufficient for acceptance.
Nature-based and ecosystem-based approaches are in scope only as engineered, quantified work — for example, green-grey infrastructure with measured hydraulic or thermal performance, or ecosystem-based interventions with instrumented outcomes. Purely qualitative, policy-only, or conceptual contributions without a technical artefact or quantified evaluation fall outside the IEEE Xplore eligibility line and will be desk-rejected without review.