Towards Machine Learning of Predictive Models from Ecological Data

• Published in: Inductive Logic Programming Vol. 9046; pp. 154 - 167
• Main Authors: Tamaddoni-Nezhad, Alireza, Bohan, David, Raybould, Alan, Muggleton, Stephen
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 01.01.2015; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Artificial intelligence; Computer programming / software development; Functional Food Web; General Predictive Rule; Mathematical theory of computation; Meta-interpretive Learning (MIL); Predicate Invention; Present Initial Results
• ISBN: 9783319237077; 3319237071
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-23708-4_11

In a previous paper we described a machine learning approach which was used to automatically generate food-webs from national-scale agricultural data. The learned food-webs in the previous study consist of hundreds of ground facts representing trophic links between individual species. These species food-webs can be used to explain the structure and dynamics of particular eco-systems, however, they cannot be directly used as general predictive models. In this paper we describe the first steps towards this generalisation and present initial results on (i) learning general functional food-webs (i.e. trophic links between functional groups of species) and (ii) meta-interpretive learning (MIL) of general predictive rules (e.g. about the effect of agricultural management). Experimental results suggest that functional food-webs have at least the same levels of predictive accuracies as species food-webs despite being much more compact. In this paper we also present initial experiments where predicate invention and recursive rule learning in MIL are used to learn food-webs as well as predictive rules directly from data.