Johan Mathe

Mad scientist and entrepreneur, I am interested in understanding the impact of climate change and weather on a plethora of metrics and systems. My background is applied mathematics and distributed systems. So far I have applied these skills to Flying Robots, Healthcare, Plasma Physics and Space Propulsion.

I recently co-founded Atmo, where we are creating algorithms and infrastructure to understand the impact of weather and climate change two orders of magnitude faster than the current state of the art.

Cultivating playfulness is in my opinion critical. With a dedicated crew of tinkerers, we enjoy fostering a makers mentality. One of our most recent completed projects was a remote-controlled flame-throwing inflatable kayak. We also tried to reproduce zero and negative gravity conditions in a tiny aerobatics airplane.

Email  /  Github  /  LinkedIn

Projects, Research & Patents

I'm interested in signal processing, optimization, statistics/machine learning, image processing and control theory.

PVNet: A LRCN Architecture for Spatio-Temporal Photovoltaic Power Forecasting from Numerical Weather Prediction
Johan Mathe Nina Miolane, Nicolas Sebastien, Jeremie Lequeux,
arXiv Preprint, 2019

Photovoltaic (PV) power generation has emerged as one of the lead renewable energy sources. Yet, its production is characterized by high uncertainty, being dependent on weather conditions like solar irradiance and temperature. Predicting PV production, even in the 24 hour forecast, remains a challenge and leads energy providers to keep idle - often carbon emitting - plants. In this paper we introduce a Long-Term Recurrent Convolutional Network using Numerical Weather Predictions (NWP) to predict, in turn, PV production in the 24 hour and 48 hour forecast horizons. This network architecture fully leverages both temporal and spatial weather data, sampled over the whole geographical area of interest. We train our model on a NWP dataset from the National Oceanic and Atmospheric Administration (NOAA) to predict spatially aggregated PV production in Germany. We compare its performance to the persistence model and to state-of-the-art methods.

geomstats: a Python Package for Riemannian Geometry in Machine Learning
Nina Miolane, Johan Mathe Claire Donnat, Mikael Jorda, Xavier Pennec,
arXiv Preprint, 2018
project page

A python package that performs computations on manifolds such as hyperspheres, hyperbolic spaces, spaces of symmetric positive definite matrices and Lie groups of transformations.

Performance Evaluation of the Alternating Direction Method of Multipliers
Johan Mathe

I implemented the Alternate Direction Method of Multipliers (ADMM) global consensus algorithm with the MapReduce framework and compare the resulting performance with another distributed optimization technique. We will also investigate various caveats with this implementation. More recently I implemented a version of ADMM for keras.
Project Loon Patents
  • Selection between Explore Mode and Control Mode for Aerial Vehicle (USPTO#9836063).
  • Efficient aerostat navigation by moving between atmospheric layers (USPTO#9665103)
  • Optimal altitude controller for super pressure aerostatic balloon (USPTO#9550558)

Guided Navigation of an Ultrasound Probe
Charles Cadieu, Ha Hong, Kilian Koepsell, Johan Mathe, Martin Wojtczyk

Embodiments of the invention provide for the guided navigation of an ultrasound probe. In an embodiment of the invention, an ultrasound navigation assistance method includes acquiring an image by an ultrasound probe of a target organ of a body. The method also includes processing the image in connection with an estimator such as a neural network. The processing in turn determines a deviation of a contemporaneous pose evident from the acquired image from an optimal pose of the ultrasound probe for imaging the target organ. Finally, the method includes presenting the computed deviation to an end user operator of the ultrasound probe.

Startup & Corporate Life

At Atmo we build algorithms and tools to understand the impact of climate and weather on various metrics. From renewable energy (photovoltaic and wind power) to outbreaks of malaria, from agricultural yields to fire outbreaks, climate change and weather have a huge impact on our daily lives and businesses. Our goal is to make these impacts more clear to people by providing them the right platform to empower whole kinds of analysis. From scientists to entrepreneurs, from individual farmers to fortune 500 companies.

Caption Health

I was part of the Caption Health founding team. I designed some of the first guidance and diagnostic algorithms. I spent a fair amount of time working on Rhumadic Heart Disease. With a team of Echo sonographers and pediatricians from the American Society of Echocadrigraphy we went to Kenya to help young children in remote villages get early diagnostics. Some more details in Jack's newletter.

Apollo Fusion

At Apollo I created various black box optimization methods in order to improve the performance of plasma based systems with a reactor-in-the-loop experiment system. The performance improvements led to the building of improved hall effect thrusters. I also led the design of the Power Propulsion Unit, which is the part of a satellite that converts power from the main bus to the thruster itself.

Google X, Project Loon

At X and Loon, I designed some of the original guidance algorithms and software in project Loon. That's where I started working extensively with weather data - especially wind data. I focused on optimal control and path planning. We also worked on explore exploit strategies to allow unprecedented balloon steering performance. You can find more details on this article from MIT Tech Review. This video is a good starting point if you never heard of project Loon. A great article on The Verge gives some interesting bits about loon navigation's system.


Google Software Engineer and SRE

At Google I worked on the design of distributed systems (Google File System and its successor colossus). Subsequently I worked on the census library and the first version of what's publicly known as GRPC, the google RPC library.


Gravity Experiments

After learning how to fly airplanes upside down, we decided to go and run some experiments with floating water. We tried to pour water during inverted flight, during 0 g parabolas, and rolls. This kind of aerobatics flight brings us from -1G all the way to 4Gs.

Flame-throwing Remote Controlled Kayak

We built an RC kayak using exclusively fans. To be more specific, there are no underwater moving parts - only thrusters. Two orthogonal flame throwers are mounted on top of the kayak.

Big thanks to the original template author.