AI4AGRI Newsletter N°04 – Sept. 2024


Forenote: the AI4AGRI newsletter relies on submissions from members of the project, please do not hesitate sharing AI4AGRI related news such as newly published papers, participation to conferences and events as well as informations about related events and courses. Please send your submissions at the following address: serge.molina+ai4agri@irit.fr


Member Highlight: Prof. Fabio Del Frate, Full Professor at University of Rome Tor Vergata

Prof. Fabio Del Frate is Full Professor at University of Rome “Tor Vergata” since 1999, where he is currently a Full Professor, teaching courses on Remote Sensing and Applied Electromagnetism in various Master and PhD Programs. He is the Coordinator of the “Design, Application, Regulation of UAVs” MSc program and Erasmus coordinator for the Engineering Macroarea. He is, or has been, principal investigator/project manager in several ESA and Italian Space Agency (ASI) funded research projects, author of more than 200 international scientific publications with a special focus on feature extraction algorithms from EO data using neural networks. He has been session organizer and in technical boards of International Conferences and Workshops focused on Geoscience and Remote Sensing. He has been Associate Editor for Geoscience and Remote Sensing Letters, Guest Editor for EURASIP Journal on Advances in Signal Processing and Remote Sensing. Currently he is a Member of the scientific section board of the Remote Sensing journal and Associate Editor for Frontiers of Remote Sensing. He has been a member of the ESA GOME ozone profile retrieval working group. In 2006 and 2007 he was a member of the group winning the IEEE data fusion contest. In 2015 he was appointed EUMETSAT Associate Scientist for activities regarding the estimation of precipitation rate from satellite data. From 2019 to 2022 he received an appointment by ESA as Visiting Professor at the ESA ESRIN centre to provide support in the use of AI for EO data processing. In 2006 he co-founded GEO-K srl, the 1st spin-off company of the University of “Tor Vergata”. For AI4AGRI, he is representing the Tor Vergata University and he is involved in the different workpackages. He also gave lectures during the AI4Agri summer schools and organised the program of work for the visiting researchers from the ROmanian Excellence Center on AI for Agriculture.


News

Pape Ibrahima THIAM: a new PhD student joins the AI4AGRI project!
🧑 Pape Ibrahima THIAM
📍IRIT – Toulouse (France) / INRAE Montpeller (France)
We are pleased to introduce Pape Ibrahima Thiam, a highly skilled data scientist joining the AI4AGRI project in collaboration with the O3T project. Pape holds a Master’s degree in Artificial Intelligence and Big Data from the École Supérieure Polytechnique de Dakar (ESP), with a focus on deep learning models for monitoring land use changes from satellite imagery. His extensive experience in applying AI technologies spans various domains, including satellite image analysis, soil carbon stock prediction, and land use classification. Pape has demonstrated strong expertise in machine learning, deep learning, and full-stack development, with proficiency in technologies such as Python, TensorFlow, and Google Earth Engine. His recent contributions include developing AI platforms for agricultural monitoring and environmental analysis, making him an invaluable addition to our team as we advance spatio-temporal data integration for Earth observation in agriculture.

Pape Ibrahima Thiam will be working on integrating spatio-temporal data with AI models to enhance the identification of actors, events, and dynamics in agricultural systems. His focus will include developing methods to process and analyze multimodal data, such as satellite imagery, for monitoring land use changes and predicting environmental patterns. Additionally, he will contribute to improving the representation of spatio-temporal relationships and validating agricultural dynamics using Earth observation data, supporting the AI4AGRI project’s goal of advancing AI-driven insights in sustainable agriculture.


AI4AGRI Events

AI4AGRI Monthly meeting: October
📅 Tue. 8 October – 10:00 (Fr/It time) | 11:00 (Ro time)

Șerban OPRIȘESCU visit in Université Toulouse 3 Paul Sabatier
🧑 Șerban OPRIȘESCU
📅 Tue. 24 – Sat. 28 September 2024
📍IRIT – Toulouse (France)
Șerban will participate to the UT3 team weekly research meeting as well as several PhD students’ presentations in relation to AI4Agri research topics. He will present him self some of his work on Image analysis (features, segmentation) for applications in agriculture. He will meet the different AI4Agri UT3 members and they will present their role. He will be trained on communication tools used by the UT3 team for producing web articles and the newsletter.

Image analysis (features, segmentation) for applications in agriculture
🧑 Șerban OPRIȘESCU
📅 Wed. 25 September 2024 – 11:00 (Fr time) | 12:00 (Ro time)
📍Salle des thèses, IRIT – Toulouse (France)
https://univ-tlse2.zoom.us/j/98366074118?pwd=VFVOdVdacTdtSzVNelhvei9Wa3FOQT09
Hyperspectral satellite imaging offers high spectral resolution images of a scene in hundreds of narrow spectral bands. This remote sensing technique proves to be very useful in many Earth Observation applications such as agriculture crop health assessment, land cover mapping and other tasks. The first part of the talk, after a brief presentation of the author’s research activity, shows some results on the semi-automatic estimation of the Shannon-Weaver biodiversity index in hyperspectral images. The purpose is the qualitative analysis of grassland areas. After an image segmentation based on histogram thresholding of spectral angle mapper (SAM) values, we compute the entropy for the pixels belonging to the segmented grassland areas using a clustering approach. The second part of the talk presents a weakly supervised framework for early identification of autumn wheat in PRISMA images.

Artur KAZAK visit in University of Rome Tor Vergata
🧑 Artur KAZAK
📅 Sun. 22 – Sun. 29 September 2024
📍University of Rome Tor Vergata, Rome (Italy)

Andrei RACOVITEANU visit in University of Rome Tor Vergata
🧑 Andrei RACOVITEANU
📅 Sun. 22 – Sun. 29 September 2024
📍University of Rome Tor Vergata, Rome (Italy)

AI4AGRI Monthly meeting: September
📅 Tue. 10 September – 14:00 (Fr time) | 15:00 (Ro time)
During the monthly meeting (10th of September), we discussed several points focusing on the 3rd project year as follows

  • Current DN proposal: before the summer break, UT3, in collaboration with the other AI4Agri partners, collected the PhD topics as well as additional partners to complement the consortium, and organizations for secondment. UT3 obtained a 5 k€ grant from the CNRS (AMORCE call) as well as a project engineer to help in writing the proposal. The AI4Agri partners committed to actively participate to the proposal.
  • Mobilities for September/October (see above in this newsletter)
  • NDVI Maps: AI4Agri is developping NDVI maps for farmers. We will also produce a guide to help the users reading these maps.
  • Future activities – ERN, WSW, webinar, summer school
  • New PhD student: Pape Ibrahima THIAM will join AI4Agri from the 1st of October. He is a PhD student from UT3, in collaboration with INRAE
  • Newsletter and communication: UT3 is now publishing regularly posts on the web site and developed a monthly newsletter. You can register to receive the newletter using this link: https://listes.irit.fr/sympa/subscribe/ai4agri

Ilaria Petracca and Giorgia Guerrisi PhD defense: The two defended theses were a success!
🧑 Ilaria Petracca; Giorgia Guerrisi
📅 Mon. 26 July 2024
📍University of Rome Tor Vergata, Rome (Italy)
Ilaria Petracca and Giorgia Guerrisi successfully defended their PhD theses before an audience of 30 attendees, showcasing their innovative research in atmospheric science and satellite data processing. Ilaria’s work focused on utilizing advanced remote sensing technologies, neural networks, and UAS for environmental monitoring, providing significant insights into phenomena like tropical cyclones and volcanic ash clouds. Giorgia’s thesis addressed the challenges of processing vast amounts of satellite data in space-limited environments, presenting optimized AI models for tasks like change detection and image compression. Their clear presentations and thorough responses to questions demonstrated a deep understanding of their fields, earning them well-deserved recognition from the academic committee and audience.


Related Events

World Space Week 2024 (international event)
📅 Fri 4 October – Thu 10 October 2024
📍https://www.worldspaceweek.org/nations/
World Space Week is an international celebration of science and technology, and their contribution to the betterment of the human condition. The United Nations General Assembly declared in 1999 that World Space Week will be held each year from October 4-10.
World Space Week consists of space education and outreach events held by space agencies, aerospace companies, schools, planetaria, museums, and astronomy clubs around the world in a common timeframe.
World Space Week is coordinated by the United Nations with the support of the World Space Week Association (WSWA). The WSWA leads a global team of National Coordinators, who promote the celebration of World Space Week within their own countries.

source: https://www.worldspaceweek.org/about/

Startech 4.0 Nawa Edition (on-site workshop)
📅 Mon 30 September – Fri 4 October 2024
📍AGH University of Krakow, Poland
https://universeh.eu/events/startech-4-0-nawa-edition/
The “Startech 4.0 Nawa Edition” workshop, taking place from September 30 to October 4, 2024, at AGH University of Krakow, offers students a unique opportunity to develop a business model based on Earth observation data. This free, English-language workshop is designed to guide participants through the key steps of launching a start-up, including team formation, identifying and analyzing problems, exploring competitive solutions, preparing value propositions, and evaluating revenue streams and cost structures. The program will also include preparation for pitching, ensuring students are equipped to present their ideas effectively. With accommodation and travel funded for international students, this week-long workshop provides invaluable support and education, making it an ideal platform for aspiring entrepreneurs. Applications are open until June 30, 2024.

European Researchers’ Night 2024 (international event)
📅 Fri 27 September 2024
https://marie-sklodowska-curie-actions.ec.europa.eu/calls/european-researchers-night-and-researchers-at-schools-2024-2025
The European Researchers’ Night takes place every year, on the last Friday of September[1]. It supports events that can last up to two days: they can start on Friday and continue the following day. Pre-events, prior to the main event, and related post-events, such as wrap-up meetings or small-scale follow-up events, can also be organised. It is the occasion for a Europe-wide public and media event for the promotion of research careers.

The European Researchers’ Night targets the general public, addressing and attracting people regardless of the level of their scientific background, with a special focus on young people and their families, pupils and students, and notably those who do not have easy access to, and thus are less inclined to engage in STEAM fields (science, technology, engineering, arts and mathematics) or research activities.

As part of the European Researchers’ night the AI4AGRI team will have the following stands/activities:

  • Potato – the first vegetable in Space
  • Colors and spectra (matching colors with their spectra, forming colors from red, green and blue primary colors)
  • From light to color (light diffraction through a prism and how vegetables and leaves look under filtered light)

source: https://ec.europa.eu/info/funding-tenders/opportunities/portal/screen/opportunities/topic-details/horizon-msca-2023-citizens-01-01


Latest AI4AGRI Publications

Artificial Intelligence to Advance Earth Observation: A review of models, recent trends, and pathways forward (September 2024)
🧑 Devis Tuia, Konrad Schindler, Begüm Demir, Xiao Xiang Zhu, Mrinalini Kochupillai, Sašo Džeroski, Jan N. van Rijn, Holger H. Hoos, Fabio Del Frate, Mihai Datcu, Volker Markl, Bertrand Le Saux, Rochelle Schneider, Gustau Camps-Valls
https://ieeexplore.ieee.org/document/10669817/keywords#keywords
This research work explores the integration of machine learning (ML) and artificial intelligence (AI) in the field of Earth observation (EO). As satellite data continues to grow, offering global insights into environmental processes, there is a pressing need for advanced processing techniques to convert raw data into actionable information. The paper discusses recent advances in ML and deep learning (DL) methodologies, which are increasingly used in EO image processing to provide meaningful insights into areas such as land use, vegetation dynamics, and disaster monitoring. Despite these advances, challenges remain, including data fusion, physical model integration, and the complexity of EO-specific tasks. The review offers a comprehensive overview of AI’s role in EO, highlights emerging trends like hybrid AI-physics models and explainable AI, and suggests potential future research pathways, emphasizing the transformative potential of AI in addressing global challenges like climate change and biodiversity monitoring.


Related AI in Agriculture and Earth Observation material

Introduction to Machine Learning for Earth Observation (Online course)
📍https://eo-college.org/courses/introduction-to-machine-learning-for-earth-observation/
Throughout this course, you’ll embark on an enlightening journey into the realm of Machine Learning (ML) as applied to Earth Observation (EO). We’ll start by exploring the current landscape of ML for EO, shedding light on the latest advancements and addressing pertinent ethical considerations.


The AI4AGRI project received funding from the European Union’s Horizon Europe research and innovation programme under the grant agreement no. 101079136.

Publishing managers: J. Mothe & S. Molina, UT3 & UT2, IRIT, France

Manage your subscription to the AI4AGRI newsletter