Predicting Water Temperature Dynamics of Unmonitored Lakes With Meta‐Transfer Learning

Abstract

Environmental data often do not exist at the appropriate resolution or extent for decision-making or characterizing change. Models can be used to fill gaps in key ecosystem variables, such as extreme precipitation rates (Lockhoff et al., 2014), soil moisture (Mishra et al., 2017, hydrological flow (Y. Liu et al., 2017), and lake temperature (Aguilera et al., 2016), which otherwise would be unavailable at the spatial and temporal scales needed for ecological decision-making (Lovett et al., 2007). Although sensor data are increasingly prevalent, it will always be incomplete, especially for variables where observations are concentrated in a small subset of locations and the majority of locations remain unmonitored. Since observing key variables like these at scale is prohibitively costly (Caughlan & Oakley, 2001), models that can efficiently use the existing data and transfer information to unmonitored systems are critical to closing our information gaps.There are many modeling approaches for predicting complex environmental phenomena, and model choice can be viewed as a trade-off among prediction accuracy, data needs, and generalizability to new systems. Process-based (PB) models are a popular modeling choice for water resources tasks like the prediction of stream temperature (

A Review and Categorization of Artificial Intelligence-Based Opportunities in Wildlife, Ocean and Land Conservation

“…Enabled by strong leadership and embedded in business strategic goals, engagement with SDGs can lead to fruitful collaborative research partnerships and technology transfer opportunities for entrepreneurs to scale up and commercialize emerging AI-enabled technology solutions for planet, people and profits, using sustainable business models [84]. Recent applications and opportunities for further cross-sectoral and cross-industry collaboration include the use of machine learning to model an environmental system such as an aquatic ecosystem to forecast its behavior, analyze its capability to react to natural or human-induced disturbances and unforeseen events, and provide decision-making aid to implement suitable measures to protect it [85,86]. Likewise, the application of AI methods or models in a specific context, for instance the application of deep learning and meta-transfer model to make predictions in one aquatic habitat based on a model developed in another aquatic habitat [86].…”

“…Recent applications and opportunities for further cross-sectoral and cross-industry collaboration include the use of machine learning to model an environmental system such as an aquatic ecosystem to forecast its behavior, analyze its capability to react to natural or human-induced disturbances and unforeseen events, and provide decision-making aid to implement suitable measures to protect it [85,86]. Likewise, the application of AI methods or models in a specific context, for instance the application of deep learning and meta-transfer model to make predictions in one aquatic habitat based on a model developed in another aquatic habitat [86]. Another area includes beneficial symbiotic human-robot collaboration, as it allows for robots to take care of both dangerous and harmful tasks and tasks that require accuracy and care [87][88][89].…”

Deeper by the Dozen: Diving into a Database of 17,675 Depths for U.S. Lakes and Reservoirs

“…Thus, we are left with having to measure lake depth directly rather than predicting it from easily acquired data sources. Perhaps ironically, models can more easily predict lake ecosystem properties such as water temperature and water clarity than depth itself, but depth is often a key predictor variable that limits the scope and accuracy of predictions (McCullough et al 2012; Willard et al 2021).…”

Limnology and Oceanography Bulletin Volume 31 Number 1 November 2021 1–29

“…Thus, we are left with having to measure lake depth directly rather than predicting it from easily acquired data sources. Perhaps ironically, models can more easily predict lake ecosystem properties such as water temperature and water clarity than depth itself, but depth is often a key predictor variable that limits the scope and accuracy of predictions (McCullough et al 2012;Willard et al 2021).…”