Malte von Bloh

Ph.D. Student

Liesel-Beckmann-Str. 2

85354 Freising

Tel: +49 (0) 8161 71 - 3487

Fax: +49 (0) 8161 71 - 2899

Career

Malte von Bloh studied agricultural sciences at the Technical University of Munich for his Bachelor's and Master's degrees and for one semester at the TEC de Monterrey in Querétaro, Mexico. During his master's degree, he increasingly turned to computer science and, in particular, machine learning. He completed his master thesis in the computer vision group of the Remote Sensing Methodology group under Prof. Schmidhalter & Dr. Marco Körner.

His research focuses on yield forecasting and intelligent crop monitoring, in particular:

• The learning of time-sequential plant growth functions.
• Explainability & Trust Analysis of deep learning methods for agriculture-related Deep Learning
• Hybrid AI: Integrating expert knowledge into data-driven algorithms
• Improving the reliability & robustness of machine learning methods
• Linking image processing, satellite, soil, climate data and quantification of agronomic management measures

Further experience in industry included working in the computer vision department of agricultural robotics manufacturers, software QM of FMIS, and management consulting of companies with a focus on digital farming. From 2019 - 2021, he was part of a startup working on intelligent crop monitoring (computer vision, time-sequential prediction models), where he did lead the R&D. From March - June 2023 he was a visiting researcher at the lab of David Lobell at Stanford University.

Teaching

• Data science in agricultural computer science
• Interdisciplinary Projects for Computer Science students
• Data Innovation Project Supervisor

Honors

• 2018: Helmut-Claas scholarship for his bachelor thesis on the detection of nutrient contents and biomass using imaging and multispectral methods
• 2022: Förderpreis Agrarinformatik der Gesellschaft für Informatik in der Land-, Forst- und Ernährungswirtschaft e.V. (GIL) for his master thesis „Data-driven crop yield prediction to forecast in-season changes for winter wheat“

• Agricultural Technology Excellence Doctoral Thesis - Award from the CLAAS foundation for highly innovative Doctoral Thesis projects in the first year of PhD with expected high impact for science and practice

Publications

Prey, L., von Bloh, M., Schmidhalter, U., Evaluating RGB Imaging and Multispectral Active and Hyperspectral Passive Sensing for Assessing Early Plant Vigor in Winter Wheat. Sensors, 2018, 18, 2931. doi.org/10.3390/s18092931
Gackstetter, D., von Bloh, M., Hannus, V., Meyer, S.T., Weisser, W., Luksch, C. and Asseng, S., Autonomous field management–An enabler of sustainable future in agriculture, 2023, Agricultural Systems, 206, p.103607, https://doi.org/10.1016/j.agsy.2023.103607.
von Bloh, M., de S. Nóia Júnior, R., Wangerpohl, X., Oğuz Saltık, A., Haller, V., Kaiser, L. and Asseng, S., Machine learning for soybean yield forecasting in Brazil, 2023, Agricultural and Forest Meteorology, 341, 109670, https://doi.org/10.1016/j.agrformet.2023.109670

To top