Francis Thitai Ndiritu Geospatial Analyst|GIS Dev|Software Developer|GIS & EO

D

Digital Addressing System

Feb 2026 - Current (9 months)

The National Addressing Framework project is a comprehensive geospatial infrastructure initiative designed to establish a standardized and intelligent addressing system for the city through structured house numbering, street naming, and the implementation of a national postcode system. The framework integrates spatial data management, Geographic Information Systems (GIS), and geocoding technologies to create accurate, location-based address datasets that support efficient urban planning and governance. Aligned with international standards such as ISO/TC 211 for geographic information and the Universal Postal Union (UPU) addressing guidelines, the system enables the development of a unified spatial addressing database that enhances interoper

P

Photomapping for Sustainable Mobility using SLI in Nakuru

Mar 2025 - Apr 2025 (2 months)

Photo-mapping is a technical activity focused on extracting spatial data from high-resolution street-level images to enhance map detail and accuracy. This process utilizes advanced AI capabilities to automatically detect and map features, thereby improving both the quantity and quality of geospatial data. The activity leverages tools such as Mapillary and Mapilio, integrated within the iD editor for OpenStreetMap, as well as the Mapillary web platform, to streamline image analysis and feature extraction for more efficient and precise mapping.

T

The Great Rift Valley(GRV) Land Degradation Impact

Feb 2025 - Aug 2025 (7 months)

The Project aimed to develop a Business As Usual (BAU) scenario of land degradation and potential restoration opportunities in the GRV by 2030, building on the baseline developed by WRI. It also aimed to analyze the socioeconomic impacts of land degradation on food security, income, poverty and labor productivity. My roles include;
• Acquiring and compiling various spatial datasets for modeling the Business-As-Usual (BAU) scenario spanning from 2000 to 2024.
• Creating Land Use Land Cover (LULC) maps with Google Earth Engine and ENVI, and validating them using high-resolution satellite imagery.
• Generating BAU scenario and 2030 prediction rasters using the Land Cover Change Modeler (LCM) in Idrisi’s TERRSET software, and uti

D

Development of an Android Mobile Application for Learning Software Development: A Practical Approach to Building User-Fr

The project involves creating an Android mobile application designed to teach software development through a practical, hands-on approach. The app will provide interactive lessons on programming concepts, data structures, algorithms, and mobile app development, with features like coding challenges, quizzes, and a built-in code editor for users to practice. Designed with a user-friendly interface, it will allow learners to track their progress, receive instant feedback, and engage in gamified learning. This app serves as both an educational tool and a platform for beginners to gain essential coding skills and apply them in real-world scenarios.

M

Modelling and predicting the effects of climate variability on crop growth stages using machine learning: A Case Study

his project explores the use of machine learning to model and predict the impact of climate variability on maize phenology in the Muringato Catchment, Nyeri, Kenya. By analyzing key climatic factors such as temperature, precipitation, and other environmental variables, the study aims to understand how these variables influence critical crop growth stages, including the Start of Season (SOS), Peak of Season (POS), and End of Season (EOS). Leveraging a combination of remote sensing data, including vegetation indices (e.g., NDVI, VHI, and LAI), and climatic indices such as the Precipitation Condition Index (PCI) and Temperature Condition Index (TCI), the project integrates advanced machine learning techniques to develop predictive models. Thes

D

Development of an Interactive Water Quality Monitoring Application Using Google Earth Engine and Sentinel-2 Imagery: A C

The project developed a web-based application that leverages the power of Sentinel-2 satellite data and Google Earth Engine to track and assess water quality in Lake Victoria, with the goal of improving environmental monitoring, management, and decision-making for the lake and its surrounding communities.

A

Advancing GeoSpatial Artificial Intelligence-based Pest Occurrence Early Monitoring System Tool for Managing Occurrence

This project focuses on developing an advanced geospatial AI-powered early monitoring system to predict and track the occurrence of the Tomato Leaf Miner (Tuta absoluta) in Machakos County, Kenya. By combining satellite-derived environmental data such as land surface temperature and relative humidity with field observations, the system provides early warnings that help farmers take timely action. The goal is to support smallholder tomato farmers with accurate, location-specific pest forecasts and promote effective Integrated Pest Management (IPM) practices to reduce crop losses and improve productivity.

Francis Thitai Ndiritu

About

Detail

Timeline

Résumé

Francis Thitai Ndiritu

About

Detail

Behavioral traits