Supported By
Supporting agricultural researchers in Southeast Asia with web-based crop and disease risk models for sustainable rice-based cropping systems and climate-resilient farming practices
Explore Platform
AgPractices&Domains improves food security and builds climate resilience in Southeast Asia by supporting agricultural researchers in Myanmar and the Philippines with advanced crop and disease risk modeling capabilities.
Our web-based application integrates sophisticated models to simulate yield responses under different management and climate scenarios, enabling researchers to identify pest and disease risks through geospatial analytics and data-driven decision making.
Our platform developed through three phases: Shiny R prototyping, expansion to Philippines/Myanmar data, and culmination in a React JS/MariaDB/Node JS system for rice yield and disease modeling with advanced visualization capabilities.
The system enables users to simulate agricultural scenarios, assess climate risks, and make informed decisions for sustainable farming practices across diverse Southeast Asian contexts.
Comprehensive rice yield modeling under various management and climate scenarios for informed decision-making.
Advanced disease risk modeling using geospatial analytics to identify and mitigate agricultural threats.
Interactive mapping and spatial analysis tools for regional agricultural risk assessment and planning.
User-friendly interface for uploading, analyzing, and visualizing agricultural data at regional scale.
Advanced rice growth simulation model calibrated with site-specific data from Myanmar and Philippines for accurate yield predictions under local conditions.
Disease epidemiology model for rice systems, providing pest and disease risk assessments based on climate and management factors.
Historical climate data integration for model validation and future scenario analysis supporting adaptation planning.
Comprehensive risk assessment framework combining crop modeling with disease prediction for integrated farm management.
Targeted decision-making tools for sustainable agriculture practices and climate-resilient farming strategies.
Seamless integration of multiple models within a unified web-based platform for comprehensive agricultural analysis.
University of Southern Queensland (USQ) - Lead technical development and coordination
SEARCA & UPLBFI - Regional research coordination and field validation
University of Computer Studies, Yangon - Local implementation and capacity building
Lead institution providing technical expertise in agricultural modeling and platform development
Southeast Asian Regional Center for Graduate Study and Research in Agriculture
University of the Philippines Los Baños Foundation Inc. - Research and validation partner
University of Computer Studies, Yangon - Local implementation and technical support
Fully functional prototype created with simulation modules for yield and disease risk, including user interface for uploading and analyzing agricultural data at regional scale.
92 participants (53% women) across Myanmar and Philippines trained on modeling techniques and platform usage for practical agricultural decision-making.
Site-specific calibration for ORYZA and EPIRICE models improved reliability in assessing climate and disease risks under local conditions.
Platform facilitated research coordination among four partner institutions, enhancing data sharing, joint training, and long-term cooperation on agricultural research.
Training materials, sustainability strategy, and data outputs packaged for broader dissemination with peer-reviewed publication on modeling framework in preparation.
Created foundation for regional digital agricultural knowledge platform supporting sustainable rice-based cropping systems across Southeast Asia.
Expanding the AgPractices&Domains platform to support broader agricultural research and sustainable farming practices across Southeast Asia and beyond.
Extend modeling platform to support other stress-prone cropping systems including maize and vegetables across Southeast Asia.
Incorporate tool into SEARCA's regional digital platform for agricultural data and decision support with continuous updates.
Develop machine learning algorithms for near-real-time prediction of pest and disease outbreaks based on field sensor inputs.
Embed platform in partner universities' agriculture and ICT courses, ensuring sustainability through education and research.