End of Year Newsletter

  

Technology matters most where it speaks to the context in which it is built. This year wasn’t just about smarter algorithms - it was about the people asking better questions. Before we move forward, here’s a look at the work that defined our year.

Miti360 Dataset Release

  

Early this year a team from DSAIL and the Institute of Geomatics, GIS & Remote Sensing (IGGReS) collected data in Kieni Forest in February focusing on tree attributes and forest dynamics with drone technology. This collaboration captured high-resolution images and tree data, essential for advancing forest ecology, conservation, and sustainable resource management.

  

The data collection offered a thrilling opportunity to engage with nature and contribute to scientific research. Insights gained resulted in the release of the Miti360 dataset, which is an integrated, machine-learning ready dataset for individual-tree and stand-level reforestation monitoring that fuses high-resolution drone orthophotos, terrestrial stereo and single images, precise ground measurements (tree height, crown diameter, basal diameter and GPS locations), species labels, and multi-year weather time series for nearby stations.

  

The collection is designed to support detection, segmentation, species classification, and biophysical parameter estimation (e.g., crown diameter, height, biomass proxies), and to enable linking short-term growth dynamics to weather. Data is provided in standard GIS and ML formats (GeoTIFF, JPEG, JSON, SHP, time-series API) for immediate integration into research and operational pipelines.

  
  

New Team Members

  

Team work makes the dream work. This year we welcomed new team members including Mary Kariuki, Leonard Sanya, Samuel Mbugua, Emason Mutuma, Austin Kaburia and Braxton Mandara. Their contributions have strengthened our research efforts and with their addition, DSAIL continues to grow driving forward ML and AI research.

  

2025 Publications

This year’s publications featured our research, insights and evidence that underpin our work. Have a read:

•

Leveraging AI Models for Regional Weather Prediction: A Data Pipeline for Africa

•

Camera Trap Data Analysis for Grevy's Zebra Monitoring

•

Using Deep Learning Techniques to Monitor a Reforested Stand in Kenya

•

Deployment and Evaluation of the Autonomous Monitoring of Insects (AMI) System for Ecosystem Health Assessment in Kenya

•

Comparing point counts, passive acoustic monitoring, citizen science and machine learning for bird species monitoring in the Mount Kenya ecosystem

•

Self-Supervised Multi-Task Learning for the Detection and Classification of RHD-Induced Valvular Pathology

  

DSAIL Research Days 2025

On 13th and 14th November we had remarkable Research Days where we appreciated the ongoing research work at DSAIL. On the first day our conversations revolved around the various approaches we employ to solve real world problems. To spice things up, we were thrilled to welcome some fantastic guests! — Dr. Sekou L. Remy, Antony M. Gitau and Ussen Kimanuka from Google Research Africa, Clinton Oduor and Jackline Tum from Amini AI, Gabriel Kiarie from NATURAL STATE and Stephen Githinji from Institute of Design and Innovation (IDI Africa).


For the second day we took things a notch higher by going for a game drive to appreciate the biodiversity that is in our ecosystem. We visited the Aberdare National Park in Nyeri where we had the opportunity to view elephants, waterbucks, colobus monkeys among other animals in their natural habitat. This made us appreciate the role various animals play in the robustness of the ecosystem.

  
  

Machine Learning Foundations Course

  

September marked the completion of an intensive Machine Learning Foundations course led by Prof. Neil Lawrence. Over four weeks, participants from DSAIL met three times per week to build a strong understanding of machine learning fundamentals, advancing from theoretical concepts to practical implementation and a final mini-hackathon. 

  
  

Throughout the program, participants demonstrated collaboration and dedication, informally referring to themselves as the “Machine Learning Football Club (MLFC)” to reflect the team spirit. The course fostered both technical competence and a supportive learning environment. 

  

With the training concluded, participants are now prepared to apply their skills in data science, machine learning, and artificial intelligence to address real-world challenges. We extend our sincere congratulations to all participants and express our appreciation to the instructional team for their commitment and guidance.

  

All materials and winning projects are available online. Please visit to check out the season’s highlights: 

  

•

View the Winning Projects here. 

  

•

Access the Lectures here.

  

•

Review the Practicals here.

  
  

Google PhD fellowships 2025

  

Our Junior Research Fellow, Lorna Mugambi, was named a recipient of the prestigious 2025 Global Google PhD Fellowship in Health Research!

  

Lorna is a doctoral student in the Department of Electrical and Electronic Engineering at Dedan Kimathi University of Technology, supervised by Professor Ciira wa Maina.

  

Lorna's research, conducted in collaboration with paediatric cardiologist Professor Liesl Zühlke, focuses on addressing the burden of Rheumatic Heart Disease (RHD) in Africa. Her work uses advanced AI techniques, including Vision-Language Models (VLMs) and Self-Supervised Learning (SSL), to develop scalable, low-cost diagnostic tools for RHD.

  

These fellowships recognize outstanding graduate students who are conducting exceptional and innovative research in computer science and related fields, with a focus on influencing the future of technology.

  

This program provides vital direct financial support for Lorna’s PhD pursuits and connects her with a dedicated Google Research Mentor, reinforcing Google’s commitment to nurturing the academic community.

  

We are incredibly proud of Lorna's achievement and look forward to the continued success and impact of her research.

  

2025 Events

  
  

We had the opportunity to participate in a number of events this year which allowed us to interact with fellow researchers and share our work to wider audiences.  The events included:

•

IST Africa 2025

•

Data Science Africa (DSA) 2025

•

EXCLAIM 2025

•

IndabaX Kenya AI Summit 2025

•

University of Leeds visit

•

African Computer Vision Summer School (ACVSS) 2025

•

Space Summer Camp 2025

•

AfriLang AI 2025

•

Deep Learning Indaba 2025

•

AI4D Partners meeting

•

African-Next-Voices Data Collection Workshop

•

DSAIL AI in Health Workshop

•

TAHMO Workshop

•

Open Hardware Summit 2025

These events encouraged us to push new frontiers in research and rejuvenated us on where to put our energy in as far as research is concerned. 2026 can only get better.

  
  

You’ve made it this far. Check out our major wins in our 2025 Wrapped.

  
  

Thank you to Our Sponsors

Huge thanks to our sponsors for providing the resources that steer our research work forward.

arm
giz
IDRC
UK International Development
Google
Lacuna Fund
Data Science Africa

Our Partners

TAHMO
ETH Zurich
University of Cambridge
  
  
  

Copyright © 2025 DSAIL

  

Dedan Kimathi University of Technology - Nyeri, Kenya

  

Subscribe to our newsletter here to stay updated on what we do.