There is a growing consensus that solutions to complex science and engineering problems require novel methodologies that are able to integrate traditional physics-based modeling approaches with state-of-the-art machine learning (ML) techniques. This article provides a structured overview of such techniques. Application-centric objective areas for which these approaches have been applied are summarized, and then classes of methodologies used to construct physics-guided ML models and hybrid physics-ML frameworks are described. We then provide a taxonomy of these existing techniques, which uncovers knowledge gaps and potential crossovers of methods between disciplines that can serve as ideas for future research.

The global decline of water quality in rivers and streams has resulted in a pressing need to design new watershed management strategies. Water quality can be affected by multiple stressors including population growth, land use change, global warming, and extreme events, with repercussions on human and ecosystem health. A scientific understanding of factors affecting riverine water quality and predictions at local to regional scales, and at sub‐daily to decadal timescales are needed for optimal management of watersheds and river basins. Here, we discuss how machine learning (ML) can enable development of more accurate, computationally tractable, and scalable models for analysis and predictions of river water quality. We review relevant state‐of‐the art applications of ML for water quality models and discuss opportunities to improve the use of ML with emerging computational and mathematical methods for model selection, hyperparameter optimization, incorporating process knowledge into ML models, improving explainablity, uncertainty quantification, and model‐data integration. We then present considerations for using ML to address water quality problems given their scale and complexity, available data and computational resources, and stakeholder needs. When combined with decades of process understanding, interdisciplinary advances in knowledge‐guided ML, information theory, data integration, and analytics can help address fundamental science questions and enable decision‐relevant predictions of riverine water quality.

Lakes and reservoirs, as most humans experience and use them, are dynamic bodies of water, with surface extents that increase and decrease with seasonal precipitation patterns, long-term changes in climate, and human management decisions. This paper presents a new global dataset that contains the location and surface area variations of 681,137 lakes and reservoirs larger than 0.1 square kilometers (and south of 50 degree N) from 1984 to 2015, to enable the study of the impact of human actions and climate change on freshwater availability. Within its scope for size and region covered, this dataset is far more comprehensive than existing datasets such as HydroLakes. While HydroLAKES only provides a static shape, the proposed dataset also has a timeseries of surface area and a shapefile containing monthly shapes for each lake. The paper presents the development and evaluation of this dataset and highlights the utility of novel machine learning techniques in addressing the inherent challenges in transforming satellite imagery to dynamic global surface water maps.

This paper presents an application of a novel machine-learning framework on MODIS (moderate-resolution imaging spectroradiometer) data to map burned areas over tropical forests of South America and South-east Asia. The RAPT (RAre Class Prediction in the absence of True labels) framework is able to build data adaptive classification models using noisy training labels. It is particularly suitable when expert annotated training samples are difficult to obtain as in the case of wild fires in the tropics. This framework has been used to build burned area maps from MODIS surface reflectance data as features and Active Fire hotspots as training labels that are known to have high commission and omission errors due to the prevalence of cloud cover and smoke, especially in the tropics. Using the RAPT framework we report burned areas for 16 MODIS tiles from 2001 to 2014. The total burned area detected in the tropical forests of South America and South-east Asia during these years is 2,071,378 MODIS (500 m) pixels (approximately 520 K sq. km.), which is almost three times compared to the estimates from collection 5 MODIS MCD64A1 (783,468 MODIS pixels). An evaluation using Landsat-based reference burned area maps indicates that our product has an average user’s accuracy of 53% and producer’s accuracy of 55% while collection 5 MCD64A1 burned area product has an average user’s accuracy of 61% and producer’s accuracy of 27%. Our analysis also indicates that the two products can be complimentary and a combination of the two approaches is likely to provide a more comprehensive assessment of tropical fires. Finally, we have created a publicly accessible web-based viewer that helps the community to visualize the burned area maps produced using RAPT and examine various validation sources corresponding to every detected MODIS pixel.

Timely and accurate monitoring of tree crop extent and productivities are necessary for informing policy-making and investments. However, except for a very few tree species (e.g., oil palms) with obvious canopy and extensive planting, most small-crown tree crops are understudied in the remote sensing domain. To conduct large-scale small-crown tree mapping, several key questions remain to be answered, such as the choice of satellite imagery with different spatial and temporal resolution and model generalizability. In this study, we use olive trees in Morocco as an example to explore the two abovementioned questions in mapping small-crown orchard trees using 0.5 m DigitalGlobe (DG) and 3 m Planet imagery and deep learning (DL) techniques. Results show that compared to DG imagery whose mean overall accuracy (OA) can reach 0.94 and 0.92 in two climatic regions, Planet imagery has limited capacity to detect olive orchards even with multi-temporal information. The temporal information of Planet only helps when enough spatial features can be captured, e.g., when olives are with large crown sizes (e.g., >3 m) and small tree spacings (e.g., <3 m). Regarding model generalizability, experiments with DG imagery show a decrease in F1 score up to 5% and OA to 4% when transferring models to new regions with distribution shift in the feature space. Findings from this study can serve as a practical reference for many other similar mapping tasks (e.g., nuts and citrus) around the world.

Learning appropriate metric is critical for effectively capturing complex data characteristics. The metric learning of categorical data with hierarchical coupling relationships and local heterogeneous distributions is very challenging yet rarely explored. This paper proposes a Heterogeneous mEtric Learning with hIerarchical Couplings, HELIC, for this type of categorical data. HELIC captures both low-level value-to-attribute and high-level attribute-to-class hierarchical couplings, and reveals the intrinsic heterogeneities embedded in each level of couplings. Theoretical analyses of the effectiveness and generalization error bound verify that HELIC effectively represents the above complexities. Extensive experiments on 30 data sets with diverse characteristics demonstrate that HELIC-enabled classification significantly enhances the accuracy (up to 40.93%), compared with five state-of-the-art baselines.