Skip to content
View alimoeinkhah's full-sized avatar
0 followers · 3 following

Block or report alimoeinkhah

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
alimoeinkhah/README.md

Ali Moeinkhah

Geospatial AI & Earth Observation Specialist

Remote Sensing · GIS · Machine Learning · Spatial Data Engineering

LinkedIn · Email · GitHub Projects

Profile

I build end-to-end geospatial analytics solutions that transform satellite imagery, environmental measurements, and spatial databases into decision-ready information.

My work combines Earth observation, machine learning, GIS, and interactive visualization to address real-world challenges in urban growth, land-cover change, natural-hazard assessment, environmental monitoring, coastal analysis, and predictive analytics.

Based in Italy, I am open to opportunities in Geospatial AI, Earth Observation, Remote Sensing, GIS, Spatial Data Science, and Environmental Data Analytics.

Featured Projects

Isfahan Urban Expansion Mapping — Landsat & Machine Learning

Multi-temporal analysis of urban expansion and land-cover change in Isfahan, Iran, between 1985 and 2024.

  • Technologies: Landsat 5/9, Google Earth Engine, Python, scikit-learn, SVM, Random Forest, NDVI, NDBI
  • Results: Quantified 599.51 km² of built-up expansion, representing a 158.7% increase
  • Model performance: SVM overall accuracy of 97.4% for 1985 and 95.9% for 2024
  • Deliverables: Documented processing workflow, classified land-cover maps, transition matrix, area-change statistics, and accuracy assessment

Sondrio Landslide Susceptibility & Population Exposure WebGIS

GIS-based workflow for landslide-susceptibility modelling, validation, population-exposure assessment, and interactive web visualization in northern Sondrio, Italy.

  • Technologies: GIS, QGIS, terrain analysis, environmental-factor modelling, WorldPop, WebGIS
  • Workflow: Prepared and standardized terrain, vegetation, infrastructure, hydrological, geological, and land-cover factors
  • Results: Produced validated susceptibility classes and quantified population exposure across different hazard levels
  • Deliverables: Susceptibility maps, validation outputs, population-exposure assessment, and interactive WebGIS

Lombardy Air Quality Monitoring Web Application

Client-server geospatial platform for exploring air-quality measurements and monitoring-station data across Lombardy, Italy.

  • Technologies: Python, Dash, Flask, PostgreSQL/PostGIS, GeoPandas, Pandas, Plotly
  • Architecture: Spatial database, Flask REST API, and interactive Dash analytical interface
  • Capabilities: Station mapping, data-availability analysis, multi-sensor time-series visualization, pollutant filtering, spatial queries, and data export
  • Data: Historical air-quality measurements and monitoring-station metadata from Dati Lombardia

Tehran Local Climate Zone Mapping

Remote-sensing and machine-learning workflow for mapping Local Climate Zones across Tehran.

  • Technologies: Landsat 8, ENVI, ArcGIS, SAGA GIS, Python, Random Forest
  • Results: Achieved 84.30% overall accuracy and a Kappa coefficient of 0.83
  • Application: Spatial characterization of urban morphology and land-cover patterns for urban-climate analysis

AI4I Predictive Maintenance

Machine-learning proof of concept for predictive maintenance of industrial equipment.

  • Focus: Data preparation, exploratory analysis, feature assessment, classification, and model evaluation
  • Application: Identification of equipment-failure patterns from operational and process variables
  • Technologies: Python, Pandas, NumPy, scikit-learn, Matplotlib

Publication

Satellite-Derived Coastal Bathymetry Using Random Forest

Moeinkhah, A., Shakiba, A., & Azarakhsh, Z. (2019).
Assessment of Regression and Classification Methods Using Remote Sensing Technology for Detection of Coastal Depth: Case Study of Bushehr Port and Kharg Island.
Journal of the Indian Society of Remote Sensing.

View publication

  • Integrated Landsat 8 OLI imagery with hydrographic depth measurements
  • Evaluated Random Forest regression and classification approaches for coastal-depth prediction
  • Compared multiple visible-band combinations using RMSE, MAE, correlation, and Kappa
  • Identified Landsat bands 1–2–3–4 as the strongest tested combination
  • Demonstrated useful satellite-derived depth estimation to approximately 10 metres, with increasing error at greater depths

Core Expertise

Earth Observation & Remote Sensing

Landsat · Sentinel-2 · Google Earth Engine · NDVI · NDBI · Land-Cover Classification · Change Detection · Satellite-Derived Bathymetry

GIS & Spatial Analysis

QGIS · ArcGIS · ENVI · SAGA GIS · GeoPandas · Rasterio · PostGIS · Spatial Modelling · WebGIS

Machine Learning & Data Analysis

Python · R · Pandas · NumPy · scikit-learn · Support Vector Machines · Random Forest · Classification · Regression · Model Validation

Geospatial Applications

Urban Growth · Land-Cover Change · Natural-Hazard Assessment · Environmental Monitoring · Population Exposure · Coastal Analysis · Predictive Maintenance

Development & Visualization

Git · GitHub · SQL · PostgreSQL · Flask · Dash · Plotly · Matplotlib

Education

M.Sc. in Geoinformatics Engineering

Politecnico di Milano — Milan, Italy
2022 – October 2026

  • All academic coursework completed; thesis work completed, with final degree formalities concluding in October 2026
  • Thesis: Multi-Year Vegetation and Land-Cover Monitoring Using Sentinel-2 NDVI Time Series and Machine Learning
  • Developed monthly Sentinel-2 NDVI time-series composites for multi-year vegetation and land-cover monitoring
  • Applied and compared Support Vector Machine, Random Forest, and 1D Convolutional Neural Network classifiers
  • Produced spatially explicit land-cover maps for orchard, cropland, bareland, and urban classes
  • Conducted independent accuracy assessment using validation samples, confusion matrices, overall accuracy, and Kappa coefficient

M.Sc. in Remote Sensing and GIS — Water and Soil

Islamic Azad University, Science and Research Branch — Tehran, Iran
2013 – 2017

  • Thesis: The Feasibility of Depth Detection Using Remote Sensing Techniques
  • Integrated Landsat 8 imagery with hydrographic measurements for satellite-derived coastal bathymetry
  • Applied Random Forest regression and classification methods and evaluated performance using RMSE, MAE, correlation, and Kappa
  • Research resulted in a peer-reviewed publication in the Journal of the Indian Society of Remote Sensing

B.Sc. in Civil Engineering — Surveying

Islamic Azad University, Yazd Branch — Yazd, Iran
2007 – 2012

  • Built a technical foundation in geodesy, photogrammetry, GPS/GNSS, field surveying, and spatial data acquisition
  • Applied total stations, GPS observations, mapping methods, and surveying computations in academic and field-based projects

Professional Interests

  • Geospatial AI and spatial machine learning
  • Earth observation and satellite-image analytics
  • Environmental and urban monitoring
  • GIS automation and spatial decision-support systems
  • Geospatial databases and interactive WebGIS applications

Contact

Pinned Loading

  1. Isfahan-urban-expansion-landsat-ml Isfahan-urban-expansion-landsat-ml Public

    Multi-temporal urban expansion mapping of Isfahan, Iran (1985–2024) using Landsat imagery, NDVI/NDBI, SVM, Random Forest, and post-classification change detection.

    Python

  2. sondrio-landslide-susceptibility-webgis sondrio-landslide-susceptibility-webgis Public

    Forked from moeinp70/polimi-gis

    GIS-based landslide susceptibility mapping and interactive WebGIS for Sondrio, Italy.

    CSS

  3. tehran-local-climate-zone-mapping tehran-local-climate-zone-mapping Public

    Mapping Tehran's Local Climate Zones using Landsat 8, ENVI, SAGA GIS, and ArcGIS, with 84.30% overall accuracy and a Kappa coefficient of 0.83.

  4. SoilTexture-Classification SoilTexture-Classification Public

    Forked from hafizsarwary/SoilTexture-Classification

    Soil texture classification in Semnan Province using Sentinel-2 and Landsat-9 imagery with Random Forest and SVM models.

    Python

  5. lombardy-air-quality-monitoring-webapp lombardy-air-quality-monitoring-webapp Public

    An interactive air quality monitoring platform for Lombardy using Python, Dash, PostgreSQL/PostGIS, GeoPandas, and Plotly.

    Python

  6. landsat8-satellite-derived-bathymetry landsat8-satellite-derived-bathymetry Public

    Satellite-derived bathymetry of shallow coastal waters using Landsat 8 OLI, hydrographic reference data, and Random Forest regression and classification.

    R