Scientific machine learning

In this post, I explore the benefits and drawbacks of using empirical (ML)-based models versus mechanistic models for predicting ecosystem responses to perturbations, and further develeop a hybrid approach combining their strengths.

This blog post discusses the use of PiecewiseInference.jl, a Julia package that enables the use of machine learning to fit complex ecological models on ecological dataset.

In this tutorial, you’ll learn the basics of approximate Bayesian computation (ABC). ABC is an inference method with very little requirements in terms of the model structure - yet it can be very powerful. It is very simple to apply to any model, and to understand. We’ll play around with Julia, and we will visualize graphically the inference results, so that you can build an intuition of the inference method.

One of the challenges modellers face in biological sciences is to calibrate models in order to match as closely as possible observations and gain predictive power. Scientific machine learning addresses this problem by applying optimisation techniques originally developed within the field of machine learning to mechanistic models, allowing to infer parameters directly from observation data.