Ebrahim Jahanshiri
Geospatial Data Scientist, Data Science and Analytics Lead and Data Specialist
Hi, I’m EJ!
a passionate Data Scientist who thrives at the intersection of data, technology, and problem-solving. With a decade of experience in this vibrant field, I’ve developed a knack for transforming raw data into meaningful insights that drive strategic business decisions.
My journey in data science began with a Pentium IV computer in 1995 that allowed me to work with earliest versions of Microsoft Excel and Fortran!. I quickly learned about how to load data, create charts and even develop out-of-the-box linear regression models with some model diagnostics. I carried all these skills with me throughout my studies in the university where I worked on various projects that required complex 3D geospatial data manipulation, analysis and publications. I have mastered R in my PhD, where I developed econometrics models for prediction of house property values.
All I have learned by myself were not enough, so I have recently completed a M.S. in Data Science (a joint program with Gothenburg and Chalmers universities, Sweden). This strong academic foundation, coupled with practical experience, has allowed me to hone my skills in areas like Machine Learning, Predictive Modelling, Data Visualization, and Big Data Analytics. Over the years, I’ve had the privilege of working in diverse industry settings. My quest for unraveling the hidden patterns in data has led to successfully enhancing business operations, improving customer experiences, and predicting market trends.
My technical toolkit is extensive, incorporating languages such as Python, R, and SQL, along with expertise in platforms like TensorFlow, PyTorch, Hadoop, and Tableau. A believer in constant learning, I’m always seeking to update my skills and stay abreast of the latest industry advancements.
But beyond the algorithms and code, my true passion lies in storytelling. Data, in my eyes, is a narrative waiting to be discovered and shared. I aim to demystify the complexities of data and present it in a way that is not only comprehensible but also actionable for decision-makers.When I’m not knee-deep in data, I enjoy hiking, reading about cognitive science, and exploring the local coffee scene. I’m also an avid supporter of women in tech, dedicating part of my time to mentoring aspiring female data scientists. Welcome to my little corner on the web, where I share my projects, thoughts on data science trends, and resources for fellow data enthusiasts. I’m excited to connect, collaborate, and keep pushing the boundaries of what data can achieve.
Thank you for stopping by!
- AI for Sustainability
- Machine Learning
- Data Enineering and automation
- Geospatial Analysis and mapping
- Storytelling with Data
- Personal development
MSc Applied Data Science, 2022
Gothenburg and Chalmers Univeristies
PhD GIS and Geomatics Engineering, 2013
Universiti Putra Malaysia
MSc Precision Farming, 2008
Universiti Putra Malaysia
Bsc Engineering, 2000
Ferdowsi University of Mashhad
Skills
3D and 2D data analysis, Inferences, Hypothesis Testing, Non-parametric Statistics
Generative Adversarial Neural Networks, Random Forest
ArcGIS, QGIS, Google Earth Engine
Budgeting, Publishing, Reporting, Grant Writing, CI/CD
Tidyverse, sf, terra, ggplot, shiny
NumPy, Pandas, Scikit-learn, PyTorch, TensorFlow
PostgreSQL, MySQL, Neo4j, GraphDB
GCP (Compute Engine, Cloud APIs), Docker, VM, Apache
Experience
- Developed a database for more than 500 agronomic studies that were published across European agroclimatic zones from 1972 to 2022: https://zenodo.org/records/8406516
- Developed a crop model to assess the potential of Proso millet as a climate-resilient crop for sustainable diversification. https://zenodo.org/records/7456224
- Developed a Global knowledge base for agricultural diversification with MYSQL, PHP on Google Cloud Platform (GCP): https://github.com/geoej/RADIANT-DB
- AiSQLQury: an Retrieval Augmented Generation (RAG) based Large Language Model (LLM) extension for domain specific data augmentation: https://github.com/geoej/AiSQLquery
- MlOps: end-to-end model production with MLflow and DVC deployment: https://github.com/geoej/EndtoEndDVC
- Awarded “Realising Dynamic Value Chains for Underutilised Crops (RADIANT) - HORIZON 2020 SFS-01-2020”. H2020 European Union. Granted 220,000 Euros. https://www.radiantproject.eu
- Developed a multistage suitability assessment based on available data at local, regional and global level (SQL database, Google Earth Engine, local meteorological and prices datasets) to provide initial evidence for the economic feasibility of hemp: https://www.sciencedirect.com/science/article/abs/pii/S0926669021007640
- Developed an analysis framework for diversification in the United Kingdom, considering climate, soil, economics, and market demand. API database of 2700 crops, combined GIS and data mining to determine the most promising climate resilitent crop for the UK: https://www.mdpi.com/2077-0472/13/4/787
- Developed a data-driven approach for shortlisting underutilized crops (UCs) for sustainable agricultural diversification across Italy: https://www.mdpi.com/2073-4395/12/7/1636
- Quantified the fitness of global datasets for forest Loss quantification in Amazonia based on R and Google Earth Engine: https://github.com/geoej/ForestLossDatasets/
- Carried out spatial suitability analysis of bambara groundnut in China using stochastic environmental research and risk assessment, sub-daily swat models, cluster analysis, economic data, climate data, soil data, crop production data, and FAOSTAT data: https://onlinelibrary.wiley.com/doi/full/10.1002/fes3.358
- Lead the development of The first version of nation-wide open 3D soil database for Sri Lanka: https://www.sciencedirect.com/science/article/pii/S235234092031235X
- Utilised the Spatial Generative Adversarial Neural Networks (SpaceGAN) and machine learning models to predict soil properties at unsampled areas (due to high cost). The results show that this method can improve the accuracy of soil information.
- Spatial Generative Adversarial Networks (SpaceGANs)
- Data mining from published resources
- Machine learning models Read more: https://gupea.ub.gu.se/handle/2077/72200?show=full
- Awarded EUR 290,000 for the project: “Development of Integrated Web-Based Land Decision Support System Aiming Towards the Implementation of Policies for Agriculture and Environment”. (H2020-RUR-2017-2). https://www.landsupport.eu
- Lead a team of 24 data specialists, and software developers to develop CropBASE suite of Apps for agricultural diversification: https://www.cropbase.co.uk
- Crop suitability mapper https://www.cropbase.co.uk/src/cropgrids/cropgrids.php
- AssessCrop: the first evidence-base for new products and their nutrition from underutilised crops: https://cropbase.co.uk/src/assesscrop/assesscrop/product_compare.php
- Developed a Global Knowledge Base for agricultural diversification: https://cropbase.co.uk/cropbasev5/
- Utilised Support Vector Machines algorithm for the economic feasibility assessment of underutilised crops: https://www.sciencedirect.com/science/article/abs/pii/S0168169918306665
- Developed a suite of software and tools for diversification of agriculture for more than 10,000 farmers in South East Asia.
- A Nutrition Security Tool demonstrating the importance of Underutilised Food Crops for Sustainable Nutrition Security https://geoprocessing.shinyapps.io/underutilised/
- DSSAT-INPUT: an online DSSAT-compatible crop modelling input generator https://geoprocessing.shinyapps.io/DSSAT-INPUT-Shiny/
- Developed Data frameworks for linking data across different disciplines: https://www.myfoodresearch.com/uploads/8/4/8/5/84855864/_4__fr-2018-104.r1_nur_marahaini.pdf
- Graduate research fellowship funded the Government of Malaysia, Ministry of Higher Education
- Developed R code to compare specifications of linear regression and spatial-temporal autoregressive models in mass appraisal valuation for single storey residential property: http://psasir.upm.edu.my/id/eprint/60054
- Developed a spatial regression techniques for prediction of house property values.
- Developed PFMap macro creates continuous availability and application maps for precision farming. A stand-alone ArcGIS macro developed with ArcObjects and VBA.
- Participated in the development of Hyperspectral analysis of oil palm fruit project that to 2 patents.
- Developed a comprehensive review of spatial analysis of Property sales. The published paper has received more than 100 citation: https://core.ac.uk/download/pdf/153802057.pdf
- Developed Shiny PFMap software, soil mapper using R statistical libraries https://geoprocessing.shinyapps.io/geoprocessing/ data for testing the App: http://b.link/a69
- Developed An Automated Valuation System for real estate appraisal based on geospatial regression techniques. A standalone software based on R programming language and TCL/TK
- Graduate research fellowship funded by The Malaysian Centre of Remote Sensing (MACRES)
- Developed a complete algorithm for geostatistical analysis and mapping that would reduce the number of samples required for mapping by 70%: https://link.springer.com/article/10.1007/s12517-015-1912-6
- Developed object-oriented approach for image segmentation using LandSat data (UGSS)
- Granted RM 135,000 (Ringgit Malaysia). “Developing a cellular automata-based planning decision support system” (01-01-04-SF0979), Ministry of Science, Technology and Innovation
- Developed a metadata system for remote sensing data fusion for “Land-use Land-cover Change and Its Environmental Consequences in Southeast Asia” project
- Transcribed records for the project: “Effects of clearance and fragmentation on forest compositional change and recovery after 200 years in western New York”
- Conducted literature search for the project “land-use land-cover change research explored using self-organizing map”
Projects
Gallery
Recent Publications
PDF Code Dataset Poster Slides Video Source Document Custom Link
Recent & Upcoming Talks
Popular Topics
Contact
Drop a line to connect or alternatively schedule a meeting: