I am an Associate Professor in the Department of Earth Observation Science (EOS) at the Faculty ITC, University of Twente. My mission is to use AI and multi-temporal remote sensing imagery to address environmental related challenges at various geographic scales.

My research focuses on developing innovative data-centric AI methods to analyze multi-temporal Earth Observation (EO) data. The following challenges are addressed: developing innovative data-centric AI solutions to extract information from EO data, training algorithms in scarce-label environments, and transferability. Current research focuses also on developing a new research line on using EO and spatial data for hidden hunger challenges- an unexplored field at the interface of Earth Observation/Geo-Information, AI methods, and food security, with a wealth of scientific opportunities and societal impact.

Expertise

  • Earth and Planetary Sciences

    • Time Series
    • Satellite Image
    • Image
    • Cartography
    • Time
    • Investigation
    • Sentinel-2
    • Area

Organisations

The focus of my research is on developing methods and techniques for environmental mapping and monitoring at different geographic scales using multi-temporal images (multispectral, hyperspectral) and data-centric AI. The research provides methods and tools for mapping and monitoring slum areas, cultivated land, crop production, and crop quality.

Since 2018, I have been investigating the potential of spatial and remote sensing data and technologies for assessing the nutritional quality of crops directly linked with a global food security challenge, namely micronutrient deficiencies aka as hidden hunger. My work on hidden hunger started when I joined the EENSAT project-Ethiopian Education Network to Support Agricultural Transformation and started co-supervising a PhD candidate, Habtamu Guja Bayu, who is investigating the relationship between micronutrient deficiencies in people living on smallholder farms in Ethiopia and the nutrient content of their crops and soils [as measured through laboratory analysis]. Thanks to this research, I became aware of the scale limitations of the current methods used for assessing (macro and micro) nutrients in crop grains. Consequently, I established a network of experts in the field of imaging spectroscopy and food security and started working on assessing the potential of Earth Observation data to estimate and predict nutrient levels in crops.

I am currently (co-)supervising seven PhD students:

  1. Habtamu Guja Bayu (primary supervisor): Applying geospatial information for integrating crop, food, and nutrition for a healthier food system in rural Ethiopia (2018 - February 2024)
  2. Sina Mohammadi (primary supervisor): Deep Learning-Based Classification of Multi-Temporal Remote Sensing Images (May 2020 - April 2024)
  3. Chenxi Duan (primary supervisor): Deep learning for cloud removal from multi-temporal images (2021-)
  4. Yangyang Cao (primary supervisor): Prediction of grain protein content  using deep learning and integrated UAV and spaceborne hyperspectral images (2023 -)
  5. Zhichong Yang (primary supervisor): Mapping and monitoring crops at global scale (2023 -)
  6. Enzo Campomanes (primary supervisor): Towards User-Centric EO and Data-centric AI for Transferable Slum Mapping (2023 -)
  7. Lorraine Trento Oliviera (co-supervisor):  Earth Observation & Citizen Science for Vulnerability Assessments in Slums: A Framework for Sub-Saharan African cities (2023 -)

I am also active in the Inclusive Earth Observation for all (EO4all) working group founded by EO women scientists at ITC. The working group focuses on enhancing ITC's visibility in the EO community and policy fields, advancing EO science, promoting gender equity (inclusion) and diversity, supporting student intakes and project acquisitions led by women from new partnerships and target groups.

Since 2020, I am an Associate Editor of ISPRS Journal of Photogrammetry and Remote Sensing. This journal has an impact factor of 12.7 and is ranked 1 out of 50 in Physical Geography. 

I have also become a member of several commissions of trust and scientific societies: member of the scientific committee of the IEEE International Geoscience And Remote Sensing Symposium-IGARSS, steering committee member of the Belgian Earth Observation Research Program STEREO III, committee member for evaluating Dutch Research Council proposals, member of the Romanian National Research Council.

Publications

2024

A robust method for mapping soybean by phenological aligning of Sentinel-2 time series (2024)ISPRS journal of photogrammetry and remote sensing, 218(part B). Huang, X., Vrieling, A., Dou, Y., Belgiu, M. & Nelson, A.https://doi.org/10.1016/j.isprsjprs.2024.10.015A source-free unsupervised domain adaptation method for cross-regional and cross-time crop mapping from satellite image time series (2024)Remote sensing of environment, 314. Article 114385. Mohammadi, S., Belgiu, M. & Stein, A.https://doi.org/10.1016/j.rse.2024.114385Towards a healthier food system for rural Ethiopia: integrating food production, diets and nutrition (2024)[Thesis › PhD Thesis - Research UT, graduation UT]. University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC). Bayu, H. G.https://doi.org/10.3990/1.9789036563130Gathering, structuring, and analyzing the space-related educational programs and their courses at the Bachelor, Master, Phd, and continuous education levels. (2024)In IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 3732-3735) (International Geoscience and Remote Sensing Symposium (IGARSS)). IEEE. Belgiu, M., Al Asmar, Y., Vargas Maretto, R., La, H., Ronzhin, S., Thiemann, H., Kerkezian, S., Kolehmainen, M., Bodenan, J. D., Stupar, D., Peter, N., Petrakis, G., Maddock, C. & Detsis, E.https://doi.org/10.1109/IGARSS53475.2024.10640886Multi-feature fusion network for efficient cloud removal using SAR-optical image fusion (2024)In IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 9062-9065) (International Geoscience and Remote Sensing Symposium (IGARSS)). IEEE. Duan, C., Belgiu, M. & Stein, A.https://doi.org/10.1109/IGARSS53475.2024.10641774Stratified machine learning models for wheat yield estimation using remote sensing data (2024)In IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 1946-1949) (International Geoscience and Remote Sensing Symposium (IGARSS)). IEEE. Khechba, K., Belgiu, M., Laamrani, A., Dong, Q., Stein, A. & Chehbouni, A.https://doi.org/10.1109/IGARSS53475.2024.10641044Crop type mapping from satellite image time series using deep learning (2024)[Thesis › PhD Thesis - Research UT, graduation UT]. University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC). Mohammadi, S.https://doi.org/10.3990/1.9789036560993Efficient cloud removal network for satellite images using SAR-optical image fusion (2024)IEEE geoscience and remote sensing letters, 21, 1-5. Article 6008605. Duan, C., Belgiu, M. & Stein, A.https://doi.org/10.1109/LGRS.2024.3397875Mapping tobacco planting areas in smallholder farmlands using phenological-spatial-temporal LSTM from time-series Sentinel-1 SAR images (2024)International Journal of Applied Earth Observation and Geoinformation (JAG), 129. Article 103826. Li, M., Feng, X. & Belgiu, M.https://doi.org/10.1016/j.jag.2024.103826Mapping integrated crop–livestock systems using fused Sentinel-2 and PlanetScope time series and deep learning (2024)Remote sensing, 16(8). Article 1421. Werner, J. P. S., Belgiu, M., Bueno, I. T., Dos Reis, A. A., Toro, A. P. S. G. D., Antunes, J. F. G., Stein, A., Lamparelli, R. A. C., Magalhães, P. S. G., Coutinho, A. C., Esquerdo, J. C. D. M. & Figueiredo, G. K. D. A.https://doi.org/10.3390/rs16081421Spatially explicit active learning for crop-type mapping from satellite image time series (2024)Sensors (Switzerland), 24(7). Article 2108. Kaijage, B., Belgiu, M. & Bijker, W.https://doi.org/10.3390/s24072108Optimizing crop type mapping for fairness  (2024)[Contribution to conference › Abstract] EGU General Assembly 2024. Gorbunov, I., Gevaert, C. & Belgiu, M.https://doi.org/10.5194/egusphere-egu24-19021Few-shot learning for crop mapping from satellite image time series (2024)Remote sensing, 16(6). Article 1026. Mohammadi, S., Belgiu, M. & Stein, A.https://doi.org/10.3390/rs16061026Feature enhancement network for cloud removal in optical images by fusing with SAR images (2024)International journal of remote sensing, 45(1), 51-67. Duan, C., Belgiu, M. & Stein, A.https://doi.org/10.1080/01431161.2023.2292014Prevalence and determinants of stunting and anaemia in children aged 6–23 months: A multilevel analysis from rural Ethiopia (2024)Maternal and child nutrition, n/a(n/a), e13736. Guja, H., Belgiu, M., Baye, K. & Stein, A.https://doi.org/10.1111/mcn.13736

Research profiles

I am enthusiastically sharing my knowledge on optical remote sensing and machine learning concepts, theories, and methods in several courses taught at ITC. I am coordinating the Advanced Image Analysis course that focuses on developing a critical understanding of modern image analysis methods (machine learning and deep learning) and applying the methods to real image analysis problems. I am also teaching decision tree and random forest algorithms in the Image Analysis course.

I am supervising and co-supervising numerous MSc theses (20+ since I joined ITC) on using spatial and EO data to address societal and environmental challenges, e.g. nutrient deficiencies, developing transferable ML algorithms for crop mapping.

Courses academic year 2024/2025

Courses in the current academic year are added at the moment they are finalised in the Osiris system. Therefore it is possible that the list is not yet complete for the whole academic year.

Courses academic year 2023/2024

I am (or was)involved in several project related to using spatial and EO data for addressing pressing societal and environmental challenges:

  1. EO4Nutri-Earth Observation for estimating and predicting crop NUTRIents project - 2023-2025 (PI/donoar European Space Agency): aims at developing innovative scientific solutions that bring together the capabilities of various Earth Observation (EO) data to estimate and predict the nutrient content of soil, crop canopy, and harvested crops for several global staple grains.
  2. Sensing hidden hunger: Understanding the relationship between grains and crop canopy micronutrient contents using hyperspectral measurements under controlled experimental conditions -2023 (PI)
  3. SPACE4ALL: Mapping climate vulnerabilities of slums by combining citizen science and earth observation technology- 2023-2027 (one of the PIs/donor NWO- Dutch Research Council). The project is funded by the NWO Open Competition Domain Science M and aims to unravel the climate vulnerability of slum communities in six larger and secondary cities located in Ghana, Kenya, and Nigeria by combining CS, EO data, and AI methods.
  4. ASTRAIOS- Analysis of Skills, Training, Research, And Innovation Opportunities in Space -2023-2025 (donor/program: Horizon Europe): I am leading work package 1 focused on providing a structured analysis of the space-oriented curricula in Higher Educational Institutions (HEI) as well as in continuing education and perform a quantitative assessment of the socio-economic characteristics of the students enrolled in these courses and eventually employed in various space sectors. In addition, I am also leading the task of developing training material to fill in the skill gap identified during our project.
  5. EENSAT-Ethiopian Education Network to Support Agricultural Transformation-2017 - 2024 (donor/program: Nuffic- Dutch organization for internationalization in education): involved in co-supervising a PhD research on assessing the spatial variation of crop nutrients in rural Ethiopia
  6. Inclusive Earth Observation (EO4all) - 2022-2027 (donor/program: Faculty of Geo-information Science and Earth Observation (ITC), Ingenuity  project): project board member very active in developing a strategy to increase diversity at our faculty and in developing teaching material to promote AI developments among women
  7. Mapping agriculture production diversity from multi-temporal satellite images using Convolutional Neural Networks - 2020-2021 (PI: donor/program: Microsoft AI for Earth Grant): focused on using a cloud computing platform to map crops at large spatial extent
  8. HyNutri: Sensing “Hidden Hunger” with Sentinel-2 and Hyperspectral (PRISMA)project  - 2019-2021 (PI/donoar European Space Agency): aims at estimating and predicting the concentration of macro-nutrients (Calcium-Ca, Magnesium-Mg, Potassium-K and Phosphorus-P) and micronutrients (Iron-Fe, and Zinc-Zn) in the final agricultural production that are essential to improving human nutrition.
  9. Tailor-Made Training - Satellite and Unmanned Aerial Vehicle (UAV) Remote Sensing Applications contributing to the creation of ecologically sustainable food and water management systems in Jordan -2019-2020 (Co-PI/donor: donor/program: Nuffic- Dutch organization for internationalization in education)
  10. EO4GEO-Towards an innovative strategy for skills development and capacity building in the space geo-information sector supporting Copernicus user uptake -2018-2021 (donor/program: Erasmus+ Sector Skills Alliance): I was involved in the development of a Body Of Knowledge (BoK) for the geospatial sector.

Address

University of Twente

Langezijds (building no. 19), room 1326
Hallenweg 8
7522 NH Enschede
Netherlands

Navigate to location

Organisations

Scan the QR code or
Download vCard