In the last few decades, harmful algal blooms (HABs, also known as “red tides”) have become one of the most detrimental natural phenomena in Florida’s coastal areas. Karenia brevis produces toxins that have harmful effects on humans, fisheries, and ecosystems. In this study, we developed and compared the efficiency of state-of-the-art machine learning models (e.g., XGBoost, Random Forest, and Support Vector Machine) in predicting the occurrence of HABs. In the proposed models the K. brevis abundance is used as the target, and 10 level-02 ocean color products extracted from daily archival MODIS satellite data are used as controlling factors. The adopted approach addresses two main shortcomings of earlier models: (1) the paucity of satellite data due to cloudy scenes and (2) the lag time between the period at which a variable reaches its highest correlation with the target and the time the bloom occurs. Eleven spatio-temporal models were generated, each from 3 consecutive day satellite datasets, with a forecasting span from 1 to 11 days. The 3-day models addressed the potential variations in lag time for some of the temporal variables. One or more of the generated 11 models could be used to predict HAB occurrences depending on availability of the cloud-free consecutive days. Findings indicate that XGBoost outperformed the other methods, and the forecasting models of 5–9 days achieved the best results. The most reliable model can forecast eight days ahead of time with balanced overall accuracy, Kappa coefficient, F-Score, and AUC of 96%, 0.93, 0.97, and 0.98 respectively. The euphotic depth, sea surface temperature, and chlorophyll-a are always among the most significant controlling factors. The proposed models could potentially be used to develop an “early warning system” for HABs in southwest Florida.

Over the past two decades, persistent occurrences of harmful algal blooms (HAB; Karenia brevis) have been reported in Charlotte County, southwestern Florida. We developed data-driven models that rely on spatiotemporal remote sensing and field data to identify factors controlling HAB propagation, provide a same-day distribution (nowcasting), and forecast their occurrences up to three days in advance. We constructed multivariate regression models using historical HAB occurrences (213 events reported from January 2010 to October 2017) compiled by the Florida Fish and Wildlife Conservation Commission and validated the models against a subset (20%) of the historical events. The models were designed to capture the onset of the HABs instead of those that developed days earlier and continued thereafter. A prototype of an early warning system was developed through a threefold exercise. The first step involved the automatic downloading and processing of daily Moderate Resolution Imaging Spectroradiometer (MODIS) Aqua products using SeaDAS ocean color processing software to extract temporal and spatial variations of remote sensing-based variables over the study area. The second step involved the development of a multivariate regression model for same-day mapping of HABs and similar subsequent models for forecasting HAB occurrences one, two, and three days in advance. Eleven remote sensing variables and two non-remote sensing variables were used as inputs for the generated models. In the third and final step, model outputs (same-day and forecasted distribution of HABs) were posted automatically on a web map. Our findings include: (1) the variables most indicative of the timing of bloom propagation are bathymetry, euphotic depth, wind direction, sea surface temperature (SST), ocean chlorophyll three-band algorithm for MODIS [chlorophyll-a OC3M] and distance from the river mouth, and (2) the model predictions were 90% successful for same-day mapping and 65%, 72% and 71% for the one-, two- and three-day advance predictions, respectively. The adopted methodologies are reliable at a local scale, dependent on readily available remote sensing data, and cost-effective and thus could potentially be used to map and forecast algal bloom occurrences in data-scarce regions.

Natural and human-induced impacts on water resources across the globe continue to negatively impact water resources. Characterizing the hydrologic sensitivity to climatic and anthropogenic changes is problematic given the lack of monitoring networks and global-scale model uncertainties. This study presents an integrated methodology combining satellite remote sensing (e.g., GRACE, TRMM), hydrologic modeling (e.g., SWAT), and climate projections (IPCC AR5), to evaluate the impact of climatic and man-made changes on groundwater and surface water resources. The approach was carried out on two scales: regional (Morocco) and watershed (Souss Basin, Morocco) to capture the recent climatic changes in precipitation and total water storage, examine current and projected impacts on total water resources (surface and groundwater), and investigate the link between climate change and groundwater resources. Simulated (1979–2014) potential renewable groundwater resources obtained from SWAT are ~4.3 × 10⁸ m³/yr. GRACE data (2002–2016) indicates a decline in total water storage anomaly of ~0.019m/yr., while precipitation remains relatively constant through the same time period (2002–2016), suggesting human interactions as the major underlying cause of depleting groundwater reserves. Results highlight the need for further conservation of diminishing groundwater resources and a more complete understanding of the links and impacts of climate change on groundwater resources.

Long-term temporal and spatial information of crop type supports a wide range of applications including hydrological and climatological studies. In the U.S., yearly crop data layers (CDLs) are available starting in the early 2000s and have been developed using combined field information and sets of temporal imagery from multiple sensors. Development of long-term crop-type layers similar to CDLs is restricted by reduced accessibility to imagery and the necessary auxiliary datasets. In this study, a procedure to generate a historical crop type was developed and evaluated. Time series of Normalized Difference Vegetation Index (NDVI) datasets from Landsat 5 TM sensor for the Lower Bear Creek watershed were collected and processed. Object-based pseudo phenology curves, represented by the NDVI time series, were generated using noise filtering and dimensionality standardization procedures for the years 1985, 1990, 1995, 2000, and 2005. Classifiers were developed and evaluated using random-forest machine learning algorithms and CDL datasets as the reference. Increased generalization performance was obtained when the model was developed using multi-year datasets. This can be attributed to improved crop type representation during the training phase coupled with characterization of yearly variations due to natural (weather) and anthropogenic factors (farming management). Source of uncertainties were the presence of multiple crops within objects, phenological similarities between soybean and corn/maize, and the accuracy of CDL itself. The proposed procedure supports the development of historic crop types for long-term studies at the field scale in agricultural watersheds.

Conservation practices (CPs) are used in agricultural watersheds to reduce soil erosion and improve water quality, leading to a sustainable management of natural resources. This is especially important as more pressure is applied on agricultural systems by a growing population and a changing climate. A challenge persists, however, in optimizing the implementation of these practices given their complex, non-linear, and location-dependent response. This study integrates watershed modeling using the Annualized Agricultural Non-Point-Source model and a GIS-based field scale localization and characterization of CPs. The investigated practices are associated with the implementation of riparian buffers, sediment basins, crop rotations, and the conservation reserve program. A total of 33 conservation scenarios were developed to quantify their impact on sediment erosion reduction. This approach was applied in an ungauged watershed as part of the Mississippi River Basin initiative aiming at reducing one of the largest aquatic dead zones in the globe. Simulation results indicate that the targeted approach has a significant impact on the overall watershed-scale sediment load reduction. Among the different evaluated practices, riparian buffers were the most efficient in sediment reduction. Moreover, the study provides a blueprint for similar investigations aiming at building decision-support systems and optimizing the placement of CPs in agricultural watersheds.