Research

My research explores how we can better understand, trust, and deploy deep learning systems to support the energy transition. I work at the intersection of explainable AI, geospatial data, and renewable energy systems, combining theoretical insights with applied work on the causes and consequences of rooftop photovoltaic (PV) development.

Highlights

Kasmi, G., Brunetto, A., Fel, T., Parekh, J. (2025). One Wave To Explain Them All: A Unifying Perspective On Feature Attribution. Forty-second International Conference on Machine Learning (ICML). Link.

Kasmi, G.; Dubus, L; Saint-Drenan, Y.-M.; Blanc, P. (2025) Space-scale exploration of the poor reliability of deep learning models: the case of the remote sensing of rooftop photovoltaic systems. Environmental Data Science 4(e22). Link.

Kasmi, G., Saint-Drenan, Y. M., Trebosc, D., Jolivet, R., Leloux, J., Sarr, B., & Dubus, L. (2023). A crowdsourced dataset of aerial images with annotated solar photovoltaic arrays and installation metadata. Scientific Data 10(1), 59. Link.

These are the papers that best summarize what I've been working on. The full record is below.

Reliable and Scalable Deep Learning for the Energy Transition

This work bridges algorithm design, large-scale mapping, and applied energy analytics, and is organized along three main threads. I highlight future research directions for each thread. If one of these directions is of interest to you, feel free to contact me.

Remote Sensing of Rooftop Photovoltaic Systems

A large share of PV capacity is distributed across rooftops, but these systems are often poorly mapped and monitored. In France, this stems from fragmented information spread across stakeholders, each with their own priorities and data formats.

The core of my thesis focused on mapping rooftop PV systems and building a nationwide registry. I developed DeepPVMapper, an algorithm for detecting and characterizing rooftop PV systems at scale, and released an open-source library, PyPVRoof, for further development. Using these tools, we mapped over 500,000 systems in France and validated the results against existing datasets — showing their potential to bridge critical information gaps as PV deployment accelerates.

Today, my focus is on making these mapping methods more actionable, reliable, and computationally efficient. One emerging direction is designing an optimal pipeline that balances accuracy, computational cost, and data availability. I'm also exploring mapping in new contexts, particularly in developing countries where PV is often adopted informally.

Future research directions:

  • Optimal pipelines for efficient and accurate PV mapping.
  • Multi-label mapping for richer characterization of rooftop systems.

Methods: Reliability and Interpretability of Machine Learning Models

The use of deep learning for computer vision is now commonplace. The real challenge lies not in implementation, but in deploying these models at scale and trusting their predictions.

My PhD was designed as a cookbook to improve the reliability of neural networks applied to the remote sensing of PV systems. I notably introduced a new explainability method, the Wavelet Scale Attribution Method (WCAM, XAI in Action workshop @ NeurIPS 2023), which reveals whether models rely on shapes, textures, or other structural features — offering richer insights than standard pixel-based saliency maps.

We later expanded this into the Wavelet Attribution Method (WAM, ICML 2025), which unifies feature attribution across different modalities (images, audio, etc.). Looking ahead, I'm exploring how to select meaningful feature attribution domains (with wavelets as one example) and whether we can combine concept-based explanations (powerful but abstract) with the practicality of feature attribution.

Future research directions:

  • Revisiting the shape and texture bias (see the paper by Geirhos et al, 2019) using WAM.
  • Generalizing the generalization: I believe we can show that feature attribution can and should be made in other domains than the input domain (see the What's Next section here), the wavelet domain being one example. Domains equipped with a sense of concepts may be particularly interesting. Second, WAM generalized gradient-based feature attribution, but I think that any feature attribution method can be generalized. To tackle this second point, I would rather adopt a theoretical perspective.

Applications: PV Power Estimation and Socio-Economic Insights

Beyond methodological work, I apply these tools to tackle real-world energy challenges. The ultimate goal of rooftop PV mapping is to improve observability, enabling grid operators to produce precise estimates of rooftop PV generation.

The final chapter of my thesis introduced a simplified method for PV production estimation (see the paper here). We demonstrated that this method slightly outperforms the one currently used by the French transmission system operator (TSO) and, importantly, better accounts for self-consumption practices.

I have also co-supervised work leveraging DeepPVMapper data to analyze socio-economic patterns in PV adoption, from local to national scales.

Future research directions:

  • The impact of self-consumption on PV power prediction.
  • PV deployment vs. targets: are we on track to meet national goals?

Full Publication Record

Publications in peer-reviewed journals

  • Kasmi, G., Saint-Drenan, Y. M., Trebosc, D., Jolivet, R., Leloux, J., Sarr, B., & Dubus, L. (2023). A crowdsourced dataset of aerial images with annotated solar photovoltaic arrays and installation metadata. Scientific Data 10(1), 59. Link.
  • Kasmi, G.; Touron, A.; Blanc, P.; Saint-Drenan, Y.-M.; Fortin, M.; Dubus, L. (2024) Remote-Sensing-Based Estimation of Rooftop Photovoltaic Power Production Using Physical Conversion Models and Weather Data. Energies 17(17), 4353. Link.
  • Kasmi, G.; Dubus, L; Saint-Drenan, Y.-M.; Blanc, P. (2025) Space-scale exploration of the poor reliability of deep learning models: the case of the remote sensing of rooftop photovoltaic systems. Environmental Data Science 4(e22). Link.

International conference proceedings (peer reviewed)

  • Kasmi, G., Brunetto, A., Fel, T., Parekh, J. (2025). One Wave To Explain Them All: A Unifying Perspective On Feature Attribution. Forty-second International Conference on Machine Learning (ICML). Link.

Workshops (peer reviewed)

  • Kasmi, G., Dubus, L., Saint-Drenan, Y. M., & Blanc, P. (2023). Assessment of the Reliability of a Model's Decision by Generalizing Attribution to the Wavelet Domain. In XAI in Action: Past, Present, and Future Applications. Link.
  • Kasmi, G., Dubus, L., Saint-Drenan, Y. M., & Blanc, P. (2023). Can We Reliably Improve the Robustness to Image Acquisition of Remote Sensing of PV Systems?. In Tackling Climate Change with Machine Learning workshop at NeurIPS 2023. Link.
  • Kasmi, G., Dubus, L., Blanc, P., & Saint-Drenan, Y. M. (2022). Towards unsupervised assessment with open-source data of the accuracy of deep learning-based distributed PV mapping. In MACLEAN: MAChine Learning for EArth ObservatioN Workshop co-located with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD 2022). Link.

Oral presentations

  • Kasmi, G., Saint-Drenan, Y. M., Dubus, L. & Blanc, P. (2025). DeepPVMapper: télédétection à l'échelle nationale des installations PV sur toiture. In Journées Nationales du Photovoltaïque (JNPV), Strasbourg, France. Slides.
  • Kasmi, G., Dubus, L., Saint-Drenan, Y. M., & Blanc, P. (2025). Space-scale exploration of the poor reliability of deep learning models: the case of the remote sensing of rooftop photovoltaic systems. In Machine Learning for Sustainable Power Systems (ML4SPS) workshop at ECML-PKDD, Porto, Portugal. Slides.
  • Kasmi, G., Touron, A., Blanc, P. Saint-Drenan, Y.-M.,& Dubus, L. (2025). Enhancing Rooftop PV Observability in France: A Comparative Evaluation of Physics-based methods with the TSO's approach. In International Conference in Energy and Meteorology (ICEM), Padova, Italy. Slides.
  • Kasmi, G., Touron, A., Blanc, P. Saint-Drenan, Y.-M., Fortin, M.,& Dubus, L. (2023). Enhancing regional PV power estimation using physics-based models, solar irradiance data and deep learning. In International Conference in Energy and Meteorology (ICEM), Padova, Italy. Slides.
  • Kasmi, G., Dubus, L., Saint-Drenan, Y. M., & Blanc, P. (2022). Leveraging earth observation data and deep learning to estimate the PV output in France. In MACLEAN Workshop @Cap/RFIAP, Vannes, France. Slides.
  • Kasmi, G., Dubus, L., Saint-Drenan, Y. M., & Blanc, P. (2022). Assessment of the potential of Earth observation data and deep convolutional neural networks to improve the estimation and forecast of the solar power production in France. PVPS Tasks 16 experts meeting, 2022, Sophia-Antipolis, France.

Position papers, working papers

  • Kasmi, G., Dubus, L., Saint-Drenan, Y. M., & Blanc, P. (2024). Leveraging Artificial Intelligence to Improve the Integration of Photovoltaic Energy into the Grid. TTI 1.5 Working papers. Link

Preprints

  • Kasmi, G. (2026). OpenPVMapper: A Multi-source, Nationwide Database of Rooftop Photovoltaic Systems in France. arXiv preprint arXiv:2607.25153. Link.
  • Mbobda-Kuate, K., Kasmi, G. (2025) Is Bigger Always Better? Efficiency Analysis in Resource-Constrained Small Object Detection. arXiv preprint arXiv:2603.02142. Link.
  • Kasmi, G., Touron, A., Dubus, L., Saint-Drenan, Y.-M., & Blanc, P. (2025). Balancing Robustness and Accuracy in Rooftop PV Estimation: Benchmarking the French TSO's Approach and Physics-Based Models. SSRN preprint 5385856. Link.
  • Mehiyddine, S., & Kasmi, G. (2025). Understanding the socio-economic patterns driving the adoption of rooftop photovoltaic systems: a preliminary literature review. HAL preprint halshs-05121399. Link.
  • Trémenbert, Y., Kasmi, G., Dubus, L., Saint-Drenan, Y. M., & Blanc, P. (2023). PyPVRoof: a Python package for extracting the characteristics of rooftop PV installations using remote sensing data. arXiv preprint arXiv:2309.07143. Link.

Posters

  • Kasmi, G., Dubus, L., Saint-Drenan, Y. M., & Blanc, P. (2025). Mapping the Invisible: A Remote Sensing Audit of Rooftop PV Data in France. In AI + Environment Summit, Zurich, Switzerland.
  • Kasmi, G., Dubus, L., Saint-Drenan, Y. M., & Blanc, P. (2022). Assessment of the potential of Earth observation data and deep convolutional neural networks to improve the estimation and forecast of the solar power production in France. In 4th MADICS Symposium, Lyon, France.
  • Kasmi, G., Dubus, L., Saint-Drenan, Y. M., & Blanc, P. (2021). Solar Array Detection on Aerial Photography Based on Convolutional Neural Networks: Image of the Solar Array Characteristics and Image Backgrounds on the Out-of-domain Generalization. In SophIA Summit, Sophia-Antipolis, France.

Miscellaneous works

  • Kasmi, G., Dubus, L, Saint-Drenan, Y.-M. & Blanc, P. Looking for a frequency-based principle to predict the sensitivity of convolutional neural networks to Gaussian image perturbations.

This work in process was presented during the PhD Forum at ECML-PKDD 2022. It is a snapshot of our early attempts to use Fourier theory to explain the (lack of) robustness of a CNN classifier. This work later led to the WCAM. The manuscript is accessible here and the slides of the presentation here.

Reviewer

Journals

Nature Communications, Scientific Data, Renewable Energy, Scientific Reports, IET Renewable Power Generation, Solar RRL, Remote Sensing in Earth Systems Sciences, Land

Conferences

NeurIPS: Ethics reviewer, Conference (2026); Ethics reviewer, Benchmark and Datasets Track (2024, 2025), renamed Evaluations and Datasets Track in 2026; Reviewer, Position Paper Track (2026).

Workshops

Tackling Climate Change with Machine Learning

ICLR 2024, NeurIPS 2024 (emergency reviewer), ICLR 2025, NeurIPS 2025, NeurIPS 2026.

Interpretability

XAI in Action workshop (NeurIPS 2023), Interpretable AI: Past, Present and Future workshop (NeurIPS 2024), Actionable Interpretability Workshop (ICML 2025), Actionable Interpretability Workshop at COLM 2026.

Computer Vision

Women in Computer Vision workshop (CVPR 2024).