The references listed on the Bruno Martin Science Direct citation may be particularly helpful. I think the (waterfall) categories are identified among them also.
I have a sense that there may be important applications that span software-engineering, especially with regard to project management, risk management, and the capture of context, usability concerns, business requirements, and complexity elimination.
There are various applications of Machine Learning in Software Engineering. Some I can think of off the top of my head are learning agents designated to perform a particular task like code completion: writing short snippets of code.
Other applications like code optimization, bug detection, natural language processing also are diverse applications of Machine Learning in Software Engineering.
Machine learning (ML) is maturing, with an increasing recognition that ML can play a critical role in a wide range of critical applications such as data mining, natural language processing, image recognition, and expert systems.