The role will support the analysis and synthesis of large-scale nutrient management (Site-Specific Nutrient Management or SSNM) and fertilizer trial datasets from the Philippines and multiple countries across Asia and Africa. Building on recently completed literature reviews and database compilations, the consultant will lead efforts to harmonize, standardize, and analyze complex agronomic datasets to generate evidence-based insights on nutrient responses, yield drivers, and fertilizer management strategies in rice-based systems.

The role will contribute to the development of high-quality scientific outputs, including peer-reviewed publications and meta-analysis studies, while identifying research gaps and informing future nutrient management and fertilizer research priorities. The consultant will also explore advanced analytical and machine learning approaches to uncover patterns and support data-driven decision-making for sustainable agricultural development.

This is a remote consultancy assignment, and the consultant may be based anywhere in the Philippines, provided that all deliverables are completed and submitted within the agreed timelines.

Data Management and Processing.

• Review and understand the structure of both the compiled Philippines SSNM literature database and the multi-country NOPT data.
• Develop a standardized data dictionary and metadata documentation.
• Retrieve and compile standard deviations, standard errors, confidence intervals, or P values required for conducting meta-analyses and meta-regressions.
• Clean, standardize, and harmonize datasets from multiple studies, countries, and formats.
• Organize variables into analyzable formats.
• Address missing data, inconsistencies, duplicate entries, and outliers.
• Retrieve the yield potential of water-limited potential for each study site or production area using published literature and the Global Yield Gap Atlas (GYGA).
• Develop a reproducible data processing workflow.
• Ensure documentation of all analytical and data management procedures

Statistical Analysis and Interpretation.

• Conduct appropriate statistical and exploratory analyses, potentially including:
  • Descriptive statistics
  • Response ratio analyses
  • Yield gap analysis
  • Nutrient response trends
  • Multi-factor interaction analysis
  • Variance and sensitivity analysis
  • Subgroup analyses by location, soil type, season, etc. and pattern detection
  • Trend analyses across countries, soil types, seasons, and agroecological zones
  • Spatial and temporal analyses where applicable.
• The analyst is expected to recommend suitable analytical approaches based on the dataset structure and research
  objectives.

Meta-Analysis Support.

• Support the development of a publishable meta-analysis paper through:
  • Effect size computation
  • Meta-regression or mixed-effects modeling
  • Identification of moderators/drivers of response to fertilizers
  • Assessment of heterogeneity across studies and publication bias
  • Publication-quality tables and figures
  • Interpretation of findings in agronomic context
  • Technical contributions to manuscript preparation and scientific reporting

Machine Learning and Advanced Analytics. Clustering of response patterns
Predictive modeling, Variable importance analysis, Decision-tree or random forest approaches, and Pattern detection across agroecological conditions.

Research Gap Identification.

• Assist the team in identifying:
  • Understudied regions or agroecosystems
  • Missing nutrient interaction studies
  • Data limitations and uncertainties
  • Priority future research directions
  • Opportunities for decision-support tools or digital agriculture applications
  • Strategic recommendations for future NOPT and SSNM research

• Master of Science in Statistics, Data Science, Agronomy, Soil Science, Crop Science, or related fields; or a Bachelor’s degree with a minimum of 5 years of hands-on experience in data analysis of agronomic research.
• Demonstrated experience in agricultural data analysis, experimental data handling, statistical modeling, and meta-analysis methods.
• Strong proficiency in R programming, Data visualization, and Statistical analysis workflows.
• Experience with nutrient management studies, soil fertility datasets, crop modeling, machine learning applications in agriculture; and familiarity with mixed-effects models, meta-analysis packages in R, reproducible research workflows.
• Publication experience in peer-reviewed journals is an advantage.

Mandatory

• Strong understanding of rice nutrient management, including SSNM, fertilizer practices, and agronomic data interpretation.
• High attention to detail, especially in handling agronomic and economic data.

Preferred

• Ability to work independently, meet deadlines, and deliver high-quality outputs.
• Good communication and writing skills for preparing summaries and technical notes.
• Preferred software/platform:
  • R (highly preferred)
  • Python (acceptable supplementary skill)
  • Experience with GitHub, Quarto, RMarkdown, or reproducible workflow tools is an advantage.

Join our team and be part of our story!

Please note that only shortlisted candidates will be contacted.
This position will remain open until filled.