Because they can turn this
Deep learning is developing by the day. Most of the research on deep learning hasn’t even been published yet — it’s that new. Specifically, hydrologists have long witnessed the miscellaneous application of machine learning tools , but little has been done in terms of harnessing Deep Learning to address the hydrological questions. This need, however, seems imperative as deep learning architectures, at their current stage, are mature enough to probe underlying inter-relationships of hydrological events and exhibit the physical underpinnings with better accuracy compared to the conventional machine learning models. Advanced optimization methods deployed within the deep learning architectures enable us to examine variant hydrological regimes in a nimble, automated and highly accurate manner. Thus, I would hypothesize, deep learning will be one of the top frontiers for the next generation of hydrological analysis.
Deep learning is advancing daily — but it’s already more capable than conventional machine learning at giving decision makers the insights they need on the water sustainability issues they face. Look for deep learning to soon become a critical component in water sustainability analysis.
Which would you rather use when communicating with a non-specialist?
The single biggest competitive communications advantage for a research-driven organization: a strategic editor steeped in your subject matter.
Takeaway: If your organization wants to up its thought leadership game, find such an editor. (I can make connections. Just ask.)