Consultant- Spatial Data Scientist at Center for International Forestry Research (CIFOR)

Duties and responsibilities
Terms of Reference:

Develop and implement spatial targeting efforts for agronomy investments
Implement workflows for spatial predictions of yield responses to agronomy investments in target populations and geographies
Design and supervise ex-ante impact analyses of agronomy project activities
Development of dashboards and other means of enabling interactive information queries related to priority indicators
Organize, manage, and analyze primary data collection through focus group discussions, key informant interviews, farm household surveys, and market surveys.
Contribute to project reporting and preparation of scientific manuscripts to be published in high-impact, peer-reviewed journals.
Build institutional networks and contacts for effective functioning of current project and for developing future collaborations

Requirements
Preferred academic qualifications, skills and attitudes:

• Advanced R programming skills: programming expertise in other languages (Python, JavaScript, Julia) and computational environments such as Google Earth Engine are an asset
• Familiarity with data visualization methods and interactive dashboards (e.g., R shiny apps) is highly desirable
• Demonstrated expertise with spatial data and spatial modeling; experience with remote sensing, geo statistics, and/or spatial econometrics are an asset
• Demonstrated expertise in machine learning prediction methods, as well as other branches of applied statistics, are essential; knowledge of econometrics is a strong asset
• Ability to integrate data from multiple sources (e.g., open data, crowd-sourcing, and remote sensing)
• Training in data science, geographic information science, computer programming, statistics or other relevant methods in the context of applied natural or social sciences
• Prior experience with collection, assembly, processing and visualization of large datasets to describe agricultural productivity patterns, cropping systems resilience and corresponding explanatory factors
• Proficiency in written and spoken English
• Knowledge of agronomy, soil science, climatology or agricultural economics is an asset
• Demonstrated familiarity with smallholder farming systems is an asset

Education, knowledge and experience

• Advanced R programming skills: programing expertise in other languages (Python, JavaScript, Julia) and computational environments such as Google Earth Engine are an asset 
• Familiarity with data visualization methods and interactive dashboards (e.g., R shiny apps) is highly desirable 
• Demonstrated expertise with spatial data and spatial modeling; experience with remote sensing, geostatistics, and/or spatial econometrics are an asset 
• Demonstrated expertise in machine learning prediction methods, as well as other branches of applied statistics, are essential; knowledge of econometrics is a strong asset 
• Ability to integrate data from multiple sources (e.g., open data, crowd-sourcing, and remote sensing) 
• Training in data science, geographic information science, computer programming, statistics or other relevant methods in the context of applied natural or social sciences 
• Prior experience with collection, assembly, processing and visualization of large datasets to describe agricultural productivity patterns, cropping systems resilience and corresponding explanatory factors
• Proficiency in written and spoken English 
• Knowledge of agronomy, soil science, climatology or agricultural economics is an asset. 
• Demonstrated familiarity with smallholder farming systems is an asset.