The paper The role of artificial intelligence in achieving the Sustainable Development Goals (2020, published in Nature) should contain the information you're looking for.
In the introduction, the authors write
Here we present and discuss implications of how AI can either enable or inhibit the delivery of all 17 goals and 169 targets recognized in the 2030 Agenda for Sustainable Development. Relationships were characterized by the methods reported at the end of this study, which can be summarized as a consensus-based expert elicitation process, informed by previous studies aimed at mapping SDGs interlinkages. A summary of the results is given in Fig. 1 and the Supplementary Data 1 provides a complete list of all the SDGs and targets, together with the detailed results from this work.
For example, as stated in the supplementary data, goal 1 is
End poverty in all its forms everywhere
and the first target (1.1.) of goal 1 is
By 2030, eradicate extreme poverty for all people everywhere, currently measured as people living on less than $1.25 a day
Then the authors suggest that, according to their studies, AI may act as an inhibitor or enabler (i.e. it may be used to fight poverty) for this target.
We identified in the literature studies suggesting that AI may be an inhibitor for this target, due to the potential increase in inequalities which would hinder the achievement of this goal (1). Other references however identify AI as an enabler for this goal, in the context of using satellite data analysis to track areas of poverty and to foster international collaboration (2).
Therefore, techniques for satellite data analysis are one of the AI techniques that may be used to tackle suistainability issues.