Living in the Physics and Machine Learning Interplay for Earth Observation

10/18/2020
by   Gustau Camps-Valls, et al.
0

Most problems in Earth sciences aim to do inferences about the system, where accurate predictions are just a tiny part of the whole problem. Inferences mean understanding variables relations, deriving models that are physically interpretable, that are simple parsimonious, and mathematically tractable. Machine learning models alone are excellent approximators, but very often do not respect the most elementary laws of physics, like mass or energy conservation, so consistency and confidence are compromised. In this paper, we describe the main challenges ahead in the field, and introduce several ways to live in the Physics and machine learning interplay: to encode differential equations from data, constrain data-driven models with physics-priors and dependence constraints, improve parameterizations, emulate physical models, and blend data-driven and process-based models. This is a collective long-term AI agenda towards developing and applying algorithms capable of discovering knowledge in the Earth system.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 4

07/02/2020

A Perspective on Gaussian Processes for Earth Observation

Earth observation (EO) by airborne and satellite remote sensing and in-s...
12/14/2021

Climate-Invariant Machine Learning

Data-driven algorithms, in particular neural networks, can emulate the e...
09/18/2021

Data-driven rational function neural networks: a new method for generating analytical models of rock physics

Seismic wave velocity of underground rock plays important role in detect...
11/17/2020

Identification of state functions by physically-guided neural networks with physically-meaningful internal layers

Substitution of well-grounded theoretical models by data-driven predicti...
12/11/2020

Learning physically consistent mathematical models from data using group sparsity

We propose a statistical learning framework based on group-sparse regres...
04/16/2021

Integrating Domain Knowledge in Data-driven Earth Observation with Process Convolutions

The modelling of Earth observation data is a challenging problem, typica...
11/27/2019

Visual Physics: Discovering Physical Laws from Videos

In this paper, we teach a machine to discover the laws of physics from v...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.