ICDM 2026 Half-Day Workshop

MIDAS: Multimodal Data Mining for Sustainable Agriculture

Bringing together data mining researchers, agricultural scientists, remote sensing experts, and industry practitioners to advance robust, scalable, and impactful data-driven methods for sustainable agriculture.

Workshop Scope

Data mining for modern agricultural systems

Agriculture is rapidly becoming a data-intensive domain shaped by large-scale sensing, remote observation, simulation models, and digital farm management systems. Modern agricultural data span field and satellite imagery, weather observations, soil and environmental sensor measurements, crop simulation outputs, genotype information, and farm management records.

MIDAS focuses on mining actionable knowledge from these heterogeneous sources to improve productivity, resilience, and sustainability. The workshop emphasizes methods for temporal modelling, robustness under distribution shifts, simulation-data fusion, and decision support in highly dynamic agricultural environments.

Call for Papers

Original contributions on data mining for sustainable agriculture

We invite original contributions on both theory and practice at the intersection of data mining and agricultural systems. Submissions may address multimodal learning, spatio-temporal modelling, simulation-data fusion, robust analytics, field deployment, or decision support for digital agriculture.

Multimodal data mining for agricultural systems

Spatio-temporal data mining for crop, climate, and environmental data

Remote sensing, field sensing, and heterogeneous data integration

Data mining for crop phenotyping and plant science

Yield prediction, forecasting, and agricultural risk analytics

Robust data mining under environmental variability and distribution shifts

Simulation-data fusion with crop models and mechanistic models

Knowledge discovery and decision support for digital agriculture

Large-scale agricultural datasets, benchmarks, and deployments

Natural-language and data-driven interfaces for agricultural analytics

Contact

Questions about MIDAS?

Zijian Wang, The University of Queensland

zijian.wang@uq.edu.au