In just the past 5 years, the field of Earth observation has progressed beyond the offerings of conventional space-agency-based platforms to include a plethora of sensing opportunities afforded by CubeSats, unmanned aerial vehicles (UAVs), and smartphone technologies that are being embraced by both for-profit companies and individual researchers. Over the previous decades, space agency efforts have brought forth well-known and immensely useful satellites such as the Landsat series and the Gravity Research and Climate Experiment (GRACE) system, with costs typically of the order of 1 billion dollars per satellite and with concept-to-launch timelines of the order of 2 decades (for new missions). More recently, the proliferation of smartphones has helped to miniaturize sensors and energy requirements, facilitating advances in the use of CubeSats that can be launched by the dozens, while providing ultra-high (3–5 m) resolution sensing of the Earth on a daily basis. Start-up companies that did not exist a decade ago now operate more satellites in orbit than any space agency, and at costs that are a mere fraction of traditional satellite missions. With these advances come new space-borne measurements, such as real-time high-definition video for tracking air pollution, storm-cell development, flood propagation, precipitation monitoring, or even for constructing digital surfaces using structure-from-motion techniques. Closer to the surface, measurements from small unmanned drones and tethered balloons have mapped snow depths, floods, and estimated evaporation at sub-metre resolutions, pushing back on spatio-temporal constraints and delivering new process insights. At ground level, precipitation has been measured using signal attenuation between antennae mounted on cell phone towers, while the proliferation of mobile devices has enabled citizen scientists to catalogue photos of environmental conditions, estimate daily average temperatures from battery state, and sense other hydrologically important variables such as channel depths using commercially available wireless devices. Global internet access is being pursued via high-altitude balloons, solar planes, and hundreds of planned satellite launches, providing a means to exploit the internet of things as an entirely new measurement domain. Such global access will enable real-time collection of data from billions of smartphones or from remote research platforms. This future will produce petabytes of data that can only be accessed via cloud storage and will require new analytical approaches to interpret. The extent to which today's hydrologic models can usefully ingest such massive data volumes is unclear. Nor is it clear whether this deluge of data will be usefully exploited, either because the measurements are superfluous, inconsistent, not accurate enough, or simply because we lack the capacity to process and analyse them. What is apparent is that the tools and techniques afforded by this array of novel and game-changing sensing platforms present our community with a unique opportunity to develop new insights that advance fundamental aspects of the hydrological sciences. To accomplish this will require more than just an application of the technology: in some cases, it will demand a radical rethink on how we utilize and exploit these new observing systems.

Developing rapid and non-destructive methods for chlorophyll estimation over large spatial areas is a topic of much interest, as it would provide an indirect measure of plant photosynthetic response, be useful in monitoring soil nitrogen content, and offer the capacity to assess vegetation structural and functional dynamics. Traditional methods of direct tissue analysis or the use of handheld meters, are not able to capture chlorophyll variability at anything beyond point scales, so are not particularly useful for informing decisions on plant health and status at the field scale. Examining the spectral response of plants via remote sensing has shown much promise as a means to capture variations in vegetation properties, while offering a non-destructive and scalable approach to monitoring. However, determining the optimum combination of spectra or spectral indices to inform plant response remains an active area of investigation. Here, we explore the use of a machine learning approach to enhance the estimation of leaf chlorophyll (Chl_t), defined as the sum of chlorophyll a and b, from spectral reflectance data. Using an ASD FieldSpec 4 Hi-Res spectroradiometer, 2700 individual leaf hyperspectral reflectance measurements were acquired from wheat plants grown across a gradient of soil salinity and nutrient levels in a greenhouse experiment. The extractable Chl_t was determined from laboratory analysis of 270 collocated samples, each composed of three leaf discs. A random forest regression algorithm was trained against these data, with input predictors based upon (1) reflectance values from 2102 bands across the 400–2500 nm spectral range; and (2) 45 established vegetation indices. As a benchmark, a standard univariate regression analysis was performed to model the relationship between measured Chl_t and the selected vegetation indices. Results show that the root mean square error (RMSE) was significantly reduced when using the machine learning approach compared to standard linear regression. When exploiting the entire spectral range of individual bands as input variables, the random forest estimated Chl_t with an RMSE of 5.49 µg·cm⁻² and an R² of 0.89. Model accuracy was improved when using vegetation indices as input variables, producing an RMSE ranging from 3.62 to 3.91 µg·cm⁻², depending on the particular combination of indices selected. In further analysis, input predictors were ranked according to their importance level, and a step-wise reduction in the number of input features (from 45 down to 7) was performed. Implementing this resulted in no significant effect on the RMSE, and showed that much the same prediction accuracy could be obtained by a smaller subset of indices. Importantly, the random forest regression approach identified many important variables that were not good predictors according to their linear regression statistics. Overall, the research illustrates the promise in using established vegetation indices as input variables in a machine learning approach for the enhanced estimation of Chl_t from hyperspectral data.