
Course
Data Science, Artificial Intelligence and Geographic Information Systems (GIS) for Environmental Sciences
Scope
This is an advanced PhD course which aims to help the participant explore and understand the ease and benefit of combining the complex (spatial) data science and AI methods and techniques with the powerful capabilities of ArcGIS platform (Esri). This course explores state-of-the-art principles, methods, and techniques related to data science and artificial intelligence applications in relation to the Environmental Sciences’ major topics. We intend to train the participants in open science and towards integrated solutions of data science and Geographic Information Systems (GIS), using different types of spatial and non-spatial data relevant to solving environmental and societal problems. In this way, the participants can give a new dimension to their research by adding a spatial component to their data and being able to process, analyze, combine, and visualize the data in multiple dimensions, including time and space.
Learning goals
The participants will explore potential links between their own research questions and GIS, using their own data or using sample data (remote sensing data). This training will familiarize the participants with using ArcGIS Pro and develop or integrate a project example or tool within ArcGIS Pro and/or ArcGIS Notebooks making use of the open science libraries and frameworks - other than the platform’s default.
Contents
The course structure follows CRoss Industry Standard Process for Data Mining (CRISP-DM)workflow. Based on the best practice examples we will firstly focus on understanding structured and non-structured data, geographic and nongeographic data. For example, we will dive into image processing, working with multispectral imagery, extracting spectral profiles, and applying raster functions such as band arithmetic, band composition, and convolution.
Next, we’ll explore machine learning techniques—such as clustering, classification, and prediction—as well as deep learning approaches like image segmentation, image classification, object detection, pixel classification, text classification and text detection. These methods will be applied to a variety of data types, including satellite imagery, aerial photography, oriented imagery, ordinary imagery, and text datasets. To support this, we will leverage ArcGIS Pro’s integrated geoprocessing tools. Additionally, participants may develop and/or integrate scientific algorithms directly within the ArcGIS platform using ArcGIS Notebooks.
During the course, from day 1 to day 4, participants will have the opportunity to apply the theory during the hands-on exercises according to each day’s topic. On Day 2, participants will also begin working on an individual assignment. Each participant is expected to choose one of the following focus areas and relate it to their own research:
- Data Engineering with ArcGIS Notebooks: Importing, exploring, cleaning, and visualizing data.
- Spatial Analysis with ArcGIS Notebooks: Accessing and creating content in ArcGIS Online.
- Machine Learning with ArcGIS Notebooks: Applying common ML techniques to spatial data.
- Image Processing and Deep Learning with ArcGIS Notebooks: Performing advanced raster analysis.
- Integrating External Deep Learning Models: Connecting custom models to ArcGIS workflows.
- Using Alternative Neural Networks: Applying neural networks beyond CNNs (e.g., building your own models or using OCR—Optical Character Recognition—within ArcGIS).
- Converting Bounding Boxes to Geographic Coordinates: Transforming detected features into RD coordinate system data.
- Automation with ArcGIS Notebooks: Creating geoprocessing tools or scheduling tasks for automated execution.
- Text detection or text classification. For example, using text detection for extracting information from old documents and maps. Text classification for classifying unstructured text in multi-label classes.
By the end of the course, participants will have gained practical experience combining geospatial tools with modern data science techniques—positioning them to apply these skills directly within their own research or operational contexts.
Programme
Date | Activity | Focus |
---|---|---|
Monday 29 September | Lectures, discussion | ‘GeoAI’ in ArcGIS platform (General introduction: the spatial data science workflow- theory and practice) |
Lectures, discussion | Focusing on using vector, raster, image data and text in the ArcGIS platform | |
Exercise | Exercise a) Data enrichment, data exploration, data visualization; b) understanding image data-spatial, spectral and radiometric resolution, band arithmetic, multispectral versus hyperspectral image data. Exercise b) The students can gather and use their own data. Based on their own data, they will get an individual assignment to explore, prepare and visualize the data, which they will use further in the exercises. | |
Dinner | ||
Tuesday 30 September | Lectures, discussion | Data Engineering and Machine Learning in ArcGIS Pro: Unsupervised learning (clustering of spatial data) and supervised learning (prediction and classification of spatial data) |
Exercise | Exercise (data engineering and machine learning exercise in ArcGIS Notebooks) | |
Individual assignment | Start individual course assignment | |
Wednesday 1 October | Lectures, discussion | Supervised learning- Deep learning in ArcGIS platform part 1 (Object detection, pixel and feature classification, text detection, text classification and of predictive van tabular data) |
Exercise | Exercise -Deep learning workflow performed in ArcGIS Pro. (The student can choose to use the geoprocessing tools of ArcGIS Pro or the ArcGIS API for Python in ArcGIS Notebooks to go through the deep learning workflow) | |
Individual assignment | Working on individual course assignment | |
Thursday 2 October | Lectures, discussion | Supervised learning- Deep learning in ArcGIS platform part 2 (Change and edge detection) |
Exercise | a) Edge detection. (Based on a pre-trained model of Esri). b) Change detection on multidimensional image data (using the change detector in ArcGIS Pro, the student can calculate the changes between two ‘epochs’ on Sentinel 2 image data). | |
Individual assignment | Working on individual course assignment | |
Friday 3 October | Presentations | Presenting the individual course assignment (present and future work) |
Drinks |
The students will have one month to finalize their individual course assignment and to write a Story Map. Each student will share their Story Map with the course participants through the course Group, in ArcGIS Online or will make their Story Map publicly.
The subject of the individual research will be preferably related to the student’s research topic.
Exam
Each student will conduct a small research project based on the CRISP-DM workflow. The research question should be related to the participant’s research topic. The methodology should include one of the deep learning models presented during the course. The results of this small research will be presented in a Story Map (the Esri way of writing articles). The structure of the Story Map should be at least based on the CRISP-DM workflow. The evaluation of the StoryMap is based on the criteria described in the StoryMap’s rubric (the StoryMap’s rubric).
The students will have one month to finalize their individual course assignment and to write a Story Map. Each student will share their Story Map with the course participants through the course Group in ArcGIS Online or will make their Story Map publicly. See in the appendix for the StoryMap’s rubric. The link to the course group will be communicated on the first day of the course.
General information
Registration deadline
Early bird registration deadline: 01 August 2025
Regular registration deadline: 29 August 2025
Remark: As this is an advanced PhD course, we are committed to selecting participants who are the best fit for the course content and objectives. After completing the registration process, you will automatically receive an email containing the link to the online assessment form. The selection of participants will be based on the information you provide in this assessment.
Target group
PhDs, Postdocs, Assistant Professors, Associate Professors
Mandatory required knowledge
a) Basic ArcGIS Pro skills (Click on this link and follow the free course “Get started with ArcGIS Pro”), and the course, Learn Python in ArcGIS Pro (important for this course, the first two lessons).
b) It would be a good idea if the participants get acquainted with machine learning in ArcGIS by following one or more courses from the online learning path of the ArcGIS platform (especially if there is an exercise related to the research topic of the participant): https://learn.arcgis.com/en/paths/try-machine-learning-with-arcgis/
c) Participants need to bring their own laptops. We suggest a RAM/memory of at least 16 GB, preferably 32GB and a sufficient graphics card. See Deep learning frequently asked questions—ArcGIS Pro If.
d) WUR participants should request an ArcGIS Online account with an ArcGIS Pro license at the GeoDesk of WUR if they do not have one yet. Non-WUR participants may need to install ArcGIS Pro using the license of their institutions.
e) The participants should have at least ArcGIS Pro 3.0 because of the Text Detection and Optical Character Recognition capabilities.
f) The student should install the Deep Learning frameworks fromhttps://github.com/Esri/deep-learning-frameworks. Be aware that the Deep Learning Frameworks installer is dependent on the version of the ArcGIS Pro.
g) After installing the Deep Learning Frameworks, make a clone of your ArcGIS Pro Python environment.
h) Also very important: download the CUDA toolkithttps://developer.nvidia.com/cuda-downloads“a development environment for creating high-performance, GPU-accelerated applications”. The Deep Learning Frameworks, which you should install (see above), are GPU-enabled.
Group size
Minimum: 5
Maximum: 25
Credit points
1.5 EC
Self-study hours
Circa 8 hours (Depending on familiarity with Arc GIS Pro and Python. For those who are familiar enough, self-study is zero)
Fee
WIMEK and all other WUR PhD candidates with an approved TSP | €100 (early bird) / €150 (regular) |
SENSE PhDs with TSP | €200 (early bird) / €250 (regular) |
All other PhD candidates | €240 (early bird) / €290 (regular) |
Postdocs and staff of WUR Graduate Schools / graduate schools mentioned above | €240 (early bird) / €290 (regular) |
All other academic participants | €280 (early bird) / €330 (regular) |
Professionals from the consortium partners | €280 (early bird) / €330 (regular) |
The course fee includes coffee, tea and lunch on all 5 days, and dinner on day 1 and drinks on day 5.
The fee does not include accommodation, breakfast and dinner (apart from dinner on day 1). Accommodation is not included in the fee of the course, but there are several possibilities in Wageningen. For information on B&B’s and hotels in Wageningen please visit proefwageningen.nl/overnachten. Another option is Short Stay Wageningen. Furthermore Airbnb offers several rooms in the area. Note that besides the restaurants in Wageningen, there are also options to have dinner at Wageningen Campus.
Cancellation conditions
- Up to 8 (eight) weeks prior to the start of the course, cancellation is free of charge.
- Up to 4 (four) weeks prior to the start of the course, a fee of 50% of the full costs will be charged.
- In case of cancellation within four weeks prior to the start of the course, a fee of 100% of the full costs will be charged.
- If you do not show at all, a fee of 100% of the full costs and a fine of 100 EUR will be charged.
Mandatory required knowledge/ Preparation
a)Basic ArcGIS Pro skills – mandatory
This is an advanced PhD/postdocs course. The students need to have at least basic knowledge of ArcGIS Pro. Below are some links to help students improve their basic skills if it is necessary:
- free course “Get started with ArcGIS Pro”:https://learn.arcgis.com/en/projects/get-started-with-arcgis-pro/
b)Basic Python programming language not mandatory (a nice to have skills)
- free course “Learn Python in ArcGIS Pro” https://learn.arcgis.com/en/paths/learn-python-in-arcgis-pro/ (important for this course, the first two lessons).
c) Participants need to bring their own laptops. We suggest a RAM/memory of at least 16 GB, preferably 32GB and a sufficient graphics card. See Deep learning frequently asked questions—ArcGIS Pro If.
For participants who do not have laptops with a powerful processor (as specified above), we will provide alternative exercises.
d) WUR participants should request an ArcGIS Online account with an ArcGIS Pro license at the GeoDesk of WUR if they do not have one yet.
Non-WUR participants may need to install ArcGIS Pro using the license of their institutions.
e) The participants should have at least ArcGIS Pro 3.0 because of the Text Detection and Optical Character Recognition capabilities.
Appendix
Storymap Rubric
Item | Explanation | Point |
---|---|---|
1. Abstract | The abstract is representative for-, and shows the student's capability of connecting the theoretical concepts presented in the course with their own research. | 2 |
2.The scientific structure of the report | The StoryMap should have the structure of a scientific paper, or at least the next paragraphs: Abstract, Introduction (research question well defined), Data, Methodology/ Analysis, Evaluation and Conclusion incorporating the CRISP-DM workflow. | 2 |
3. Impact of the research | The student tries to understand and explain what the added value of GeoAI is for their research | 2 |
4. Evaluation | The evaluation is related to the research question(s) chosen GeoAI method to experiment, and, of course, the results. | 2 |
5. Conclusion | Here would be appreciated (apart from the conclusions related to the research question and to the specific GeoAI method chosen from the topics of the theory week) to make a short reflection related to using ArcGIS Pro and/or ArcGIS Notebooks to perform a GeoAI analysis. Also, it would be nice if the student were capable of explaining if they will like to further continue using GeoAI in their future research. | 2 |