An environmental crisis: science has failed; let us send in the machines

Abstract

The ecological condition of the world's waterways continues to decline under increasing pollution, human land use intensification, and/or demand for water abstraction. This is occurring despite the fact that freshwater ecologists and other water scientists have been investigating these environmental concerns for many years. Freshwater science has made considerable advances understanding the causes of this ecological decline, but we still appear to be further from halting that decline than ever before. Perhaps the scientific solutions are clear but political, social, legal or economic constraints intervene? Irrespective of the reasons, in my opinion freshwater science is failing to deal effectively with this environmental crisis. I believe that artificial intelligence devices and machine learning software may offer potential for dealing with the environmental crisis facing the world's freshwater. There are numerous, free and easy to use software packages that would enable freshwater ecologists to better understand some of the complex, nonlinear relationships in their data, and to potentially make better predictions about the effects of stressors and/or how best to mitigate them. I see a not too distant future where these devices will take over direct management of river reaches to hopefully provide more effective balancing of economic and environmental needs for water. I would like to encourage more scientists to embrace the ease and power of machine learning as a way to better interpret collected data, or at least provide an alternative perspective that may prove useful. WIREs Water 2015, 2:595–600. doi: 10.1002/wat2.1102 This article is categorized under: Water and Life > Methods

Can big data tame a “naughty” world?

“…This approach draws attention to the (changing) balance of decision making between human analysts and non‐human technologies. In the face of the sensor‐driven data “deluge” it has become apparent that traditional analytical tools and techniques are insufficient (Death ; Elliott et al ). In their place, new methods of data computation, storage, management, representation, and statistical analysis have emerged.…”

“…A second shift invoked by big data involves a movement in environmental scientists' roles towards the analysis of correlations automatically highlighted by algorithms, the aim being to identify patterns that make physical sense and develop theoretical arguments and empirical hypotheses to test these (Peters et al ). Unguided, automated exploration of big datasets is perceived as a productive way to analyze big data and compare multiple variables across space and time (e.g., Death ; Krause et al ; Pagano et al ). However, results from automated techniques can be misleading if they are not interpreted within the context of existing knowledge frameworks and the limitations of the dataset (O'Sullivan and Manson ).…”

“…If landscapes can be converted into datascapes, then what is needed is not analysis of landscapes but analysis of datascapes. Further, these changes in observational and methodological priorities could lead towards the prioritization of reanalysis of open source/public datasets over field science, triggering the “rise of the data scientist” (Levy ) and the death of the environmental expert (Death ). There is no doubt that technicians, volunteers, and citizen scientists, together with industrial and commercial data analysts, can each play valuable and important roles in collection and analysis of big datasets, but we agree with Pagano et al () that the human judgment of the environmental scientist remains critical to meaningful interpretation.…”

“…The exponential increase in our ability to acquire, store, transmit, and analyze data has led various commentators to suggest that a world of “big data” has arrived, a world in which research questions can be answered by data directly, without reference to theoretical frameworks (Miller and Goodchild ). By covering massive spatial scales and diverse scientific domains, big data and accompanying analytical techniques offer the possibility of identifying new patterns and predictors from the chaos and complexity of human and environmental processes (Death ; O'Sullivan and Manson ). Big data, it is claimed, has the potential to provide unprecedented insights into environmental systems and human behaviour and offer an improved basis for decision making in a new era of data‐informed policy (White et al ).…”

“…Big data has also been touted as key to “solving the city” (Lehrer ) and “revolutionizing” understandings of climate change vulnerability (Ford et al ), potentially leading to “miraculous solutions to well‐worn problems” (Crang , 351). With the data deluge upon us, some claim that machine learning analyses of big data may be able to succeed where “science has failed” in solving complex environmental problems (Death , 595). In this emerging infrastructure and analytics of big data, a fourth paradigm in scientific thought has been proposed (Hey et al ; Kitchin ), heralding “the end of theory” (Anderson ) and requiring an across‐the‐board revaluing of scientific practices (Elliott et al ).…”