I am a postdoc and Schmidt Science Fellow in the Ermon Lab at Stanford University. I want to help to alleviate global hunger. In my current work, I focus on statistical and machine learning models improving the prediction of crop yields in Africa, which depend on periods of drought or enhanced rainfall.
Before joining Stanford, I completed my PhD in the working group Atmospheric Dynamics at the Karlsruhe Institute of Technology (KIT) in Germany, where I worked with mathematicians to describe—at daily, weekly, and intraseasonal timescales—how different types of atmospheric waves create dry and wet periods over Africa, while demonstrating their potential for statistical rainfall forecasting.
Currently, I develop a new tropical crop forecasting model by applying statistical and machine learning methods to satellite and numerical weather data. In my Schmidt Science Fellowship year, I will draw on previous experience and expertise to develop a real-time crop-yield prediction model for Africa. With the Ermon Lab at Stanford, I aim to achieve this via a combination of real-time satellite observations, weather forecasts, and machine learning techniques. Using neural networks, I hope to also build on investigations I have previously led on the influence of variable oceanic modes such as the El-Niño in the Pacific Ocean on crop yields in Tanzania, with the goal of testing whether such models can be used as predictors for crop yield more widely.
I am also part of the Sustain Lab and am excited by the potential of interdisciplinary “computational sustainability”. I hope to contribute to this new field as it aims to address sustainability challenges through computational methods.
PhD in Atmospheric Physics, 2019
Karlsruhe Institute of Technology, Germany
MSc in Tropical and International Forestry, 2015
Georg-August-University Göttingen, Germany
BSc in Meteorology, 2012
Gutenberg University Mainz, Germany
Responsibilities include:
Rainfall over Africa varies across timescales of a few days to several weeks due to several tropical and extratropical modes of variability. Excessive rains or prolonged drought regularly result in natural disasters and have thus a severe impact on the local economy, agriculture, spread of diseases, and entire ecosystems. The dynamical nature of the atmosphere allows the existence of planetary balanced modes, which are called Rossby waves, and smaller-scale unbalanced inertio-gravity (IG) waves…
This study presents the first systematic comparison of the dynamics and thermodynamics associated with all major tropical wave types causing rainfall modulation over northern tropical Africa: the Madden–Julian oscillation (MJO), equatorial Rossby waves (ERs), tropical disturbances (TDs, including African easterly waves), Kelvin waves, mixed Rossby–gravity waves (MRGs), and eastward inertio-gravity waves (EIGs)…
Low-latitude rainfall variability on the daily to intraseasonal time scale is often related to tropical waves, including convectively coupled equatorial waves, the Madden–Julian oscillation (MJO), and tropical disturbances (TDs). Despite the importance of rainfall variability for vulnerable societies in tropical Africa, the relative influence of tropical waves for this region is largely unknown. This article presents the first systematic comparison of the impact of six wave types on precipitation over northern tropical Africa…
Accumulated precipitation forecasts are of high socioeconomic importance for agriculturally dominated societies in northern tropical Africa. In this study, we analyze the performance of nine operational global ensemble prediction systems (EPSs), which are part of the TIGGE dataset, for three regions in northern tropical Africa. […] To assess the full potential of raw ensemble forecasts across spatial scales, we apply state-of-the-art statistical postprocessing methods in form of Bayesian Model Averaging (BMA) and Ensemble Model Output Statistics (EMOS)…
In June and July 2016 the Dynamics–Aerosol–Chemistry–Cloud Interactions in West Africa (DACCIWA) project organised a major international field campaign in southern West Africa (SWA) […] The purpose of this paper is to characterise the large-scale setting for the campaign as well as synoptic and mesoscale weather systems affecting the study region in the light of existing conceptual ideas, mainly using objective and subjective identification algorithms based on (re-)analysis and satellite products…