About

With ten years of experience as a Data Scientist and GIS/Remote Sensing Analyst, I excel in harnessing the power of data all through its full life cycle from data collection, validation, aggregation, analysis and visualization. I have designed semi-automated data pipelines to optimize the data management process for monitoring and evaluation projects. Beyond that, I bring in my spatial expertise to conduct advanced geostatistical analyses and together, create accessible, user-focused deliverables - including interactive dashboards, maps, detailed report tables, charts, and graphs - all crafted to support effective data-driven decision-making and optimization of project's strategic objectives. My work is anchored in thorough research and analysis to identify cutting-edge solutions. Together, we can turn data into powerful, actionable insights.

Skills

  • GIS and Remote Sensing
    10
  • Python
    10
  • Data visualization with PowerBI and Tableau
    8
  • Data Science
    10
  • Data Analysis
    9
  • Monitoring and Evaluation (Data Management)
    9
  • Quantitative and Qualitative data analysis
    7

Experience

Joan Gathu

Work experience
  • Responsible for managing and processing quantitative and qualitative data, carrying out advanced spatial analysis, data modelling, map visualizations, dashboard development and providing monitoring and evaluation support for USAID’s Food Security and Third-Party Monitoring Project and UNICEF’s Nutrition Improvement for Children through Cash and Health Education (NICHE) project throughout their whole data and project cycle, among other projects.
  • Project leadership and cross-functional team coordination: Designed, digitized and tested the Monitoring and Evaluation tools for quantitative and qualitative data collection utilizing KOBO platforms, ensuring robust data capture. Collaborated with the survey team, participating in field activities; training, survey supervision, providing technical support to field teams, ensuring data quality and adherence to protocols. Streamlined data collection for through innovative GIS solutions.
  • Automation of Data Management and Reports. Developed pipelines using Python programming to automate the process of extracting quantitative and qualitative data, cleaning, wrangling, manipulating, decoding, labelling, performing quality control, conducting aggregation, running statistical analysis, deriving indicators, creating data visualizations and generating high-quality analytical reports tables, for integration into dashboards, reports and presentations. Automating reporting using python. Employed python dictionaries and packages: Pandas, Numpy, Matplotlib, Plotly, Seaborn, Plotly, Shiny, among others
  • Data validation and Quality control mechanism. Ensuring that as data came in, it maintained its integrity and where necessary, the data was corrected in cases of human error. Developed mechanisms within the pipeline to check for outliers. Based on the learnings, make changes to existing data and information
  • Data Integration. Enable data-informed decision-making by extracting and summarizing operational and programmatic insights, while gathering organizational knowledge from various departments to ensure shared learnings shape strategic planning.
  • Advanced data analysis: Conducting statistical analysis, including ANOVA, hypothesis testing, and regression modeling, to derive meaningful insights from data.
  • Advanced spatial data analysis, modeling and automation using ArcGIS Pro & Python programming: Designed and implemented spatial models for predicting outcomes and impacts, advanced spatial analyses to identify trends, patterns, and relationships for informed decision-making. These models involved linking rainfall patterns with NDVI indices to compile reported on-ground observations and analyze their connection to market price trends.
  • Data visualization: Developing and publishing dynamic, interactive dashboards using platforms such as Power BI, Tableau and, Superset to effectively highlight key program outcomes and trends, while improving data accessibility and usability for end-users. Creating precise and informative data reports that effectively present relevant information, are accessible to individuals from diverse backgrounds, and can be easily understood.
  • Cartographic visualization to enrich report content: Produced quality cartographic visualization for integration into project report to uncover hidden patterns and effectively communicate insights. Leverage on using platforms such as Superset, ArcGIS Pro, and GIS Online to produce maps and interactive dashboards.
  • Remote sensing data interpretation and analysis: Employed advanced satellite image processing techniques that extract, analyze, derive, interpret, and visualize satellite data, applying software such as ENVI, GEOCLIM and python packages like Numpy, scikit-image, scikit-learning and Tensorflow to develop robust classification models that identify land cover types from satellite imagery.
  • Data Storage Maintenance: Facilitated efficient data management on the KOBO server, SharePoint and CKAN platform, ensuring data security, smooth accessibility for data users and enhanced user functionality.
  • Offered technical support and guidance to GIS users within the organization.

Related persons

bibiana chalweElectronic Data Collection . qualitative and quan