Christian Requena Mesa
|
PhD Student | 
|
Research interests
I am an environmental scientist hugely invested on machine learning and artificial intelligence. I am interested on how novel computer vision and generative algorithms can improve environmental monitoring, as well as, how artificial general intelligence can lead to a better environmental management and decision making. My vision for environmental problem solving relies on the use of deep learning as a dynamic adviser to help us set the rules by which humans best interact with the environment. I believe that current artificial intelligence can help in finding the equilibrium that maximizes both: the benefits we get from nature, and the stability and resilience of the natural systems.
Ph.D. project
Data-driven modeling (deep learning) of temporal and spatial context effects in Earth System data.
Education
- Since 08/2017 PhD Student at the German Aerospace Center (DLR), FSU-Jena and the Max-Plank Institute for Biogeochemistry in Jena, DE
- 09/2015-06/2017 EMMC International Master in Applied Ecology (Triple Master)
MSc in Ecology (Evolutionary Ecology). Université de Poitiers , France.
MSc in Ecology (Environmental Quality Assesment). Universidade de Coimbra , Portugal.
MSc in Ecology (Biodiversity assessment, conservation and management). UFRGS , Brazil.
- 10/2010-07/2015 BSc in Environmental Science. Universidad de Málaga, Spain.
Bach. study abroad at Georgia State University, GA, USA. (08/2012-05/2013)
Bach. study abroad at Seoul National University, South Korea. (09/2013-01/2014)
Bach. study abroad at Radboud Universiteit Nijmegen, Netherlands. (02/2014-05/2014)
Publications
-Lütjens, B., Leshchinskiy, B., Requena-Mesa, C., Chishtie, F., Newman, D., Gal, Y., Raissi, C. (2021, under review). Physics informed GAN for coastal flood visualization. IEEE TNNLS Special Issue on Deep Learning for Earth and Planetary Geosciences.
-Requena-Mesa, C.*, Benson, V.*, Runge, J., Reichstein, M., Denzler, J. (2021). EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task. Computer Vision and Pattern Recognition CVPR2021, EarthVision2021.
-Bates, A., Primack, R., PAN-Environment Consortium, Duarte, C. (2021). Diverse Human-Nature Interactions Revealed by the Global COVID-19 Lockdown. Submitted to Nature Comms (Under review)
-Requena-Mesa, C.*, Benson, V.*, Runge, J., Reichstein, M., Denzler, J. (2020). EarthNet2021: A novel large-scale dataset and challenge for forecasting localized climate impacts. NeurIPS2020, Tackling Climate Change with Machine Learning.
-Tibau, X. A., Reimers, C., Requena-Mesa, C. (2020). Spatio-temporal VAE models in weather and climate forecasting (Chapter 11). In book, Deep learning for the Earth Sciences.
-Gomez-chova, L., Requena-Mesa, C., Laparra, V. (2020). Generative Adversarial Networks in the geosciences (Chapter 10). In book, Deep learning for the Earth Sciences.
-Reimers, C., Requena-Mesa, C. (2020). Deep Learning - an Opportunity and a Challenge for Geo- and Astrophysics (Chapter 13). In book, Knowledge Discovery in Big Data from Astronomy and Earth Observation, pp. 251-266.
-Requena-Mesa, C., Reichstein, M., Mahecha, M., Kraft, B., & Denzler, J. (2019, September). Predicting Landscapes from Environmental Conditions Using Generative Networks. In German Conference on Pattern Recognition (pp. 203-217). Springer, Cham.
-Kraft, B., Jung, M., Körner, M., Requena-Mesa, C., Cortés, J., & Reichstein, M. (2019). Identifying dynamic memory effects on vegetation state using recurrent neural networks. Frontiers in Big Data, 2.
-Tibau, X. A.*, Requena-Mesa, C.*, Reimers, C.*, Denzler, J., Eyring, V., Reichstein, M., & Runge, J. (2018) SupernoVAE: VAE Based Kernel-PCA for Analysis of Earth Spatio-Temporal Data. Climate Informatics Workshop 2018 proceedings.
-Requena-Mesa, C., Reichstein, M., Mahecha, M., Kraft, B., & Denzler, J. (2018, July). Predicting landscapes as seen from space from environmental conditions. In IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium (pp. 1768-1771). IEEE.
-Requena-Mesa, C. "The ecosystem services of the Cerrado trees: modelling, distribution mapping and implications for conservation." (2017).
-Requena-Mesa, C., & Niell, F.X. (2015). The ecosystem Service of an Atlantic Salt-Marsh as a Carbon Sink. Modelling, Balance and Simulation. VIII Symposium on the Iberian Atlantic Margin (Proceedings), Malaga (Spain), 21-23 September, Ediciones Sia Graf., pp. 33-36. Legal Deposit Number: MA 1272-2015. Access: https://issuu.com/gemar/docs/libro_comunicaciones-mia15-pag-0-38/46
*Denotes equal contribution