Despite the abundance of research on coral reef change detection, few studies have been conducted to assess the spatial generalization principles of a live coral cover classifier trained using remote sensing data from multiple locations. The aim of this study is to develop a machine learning classifier for coral dominated benthic cover-type class (CDBCTC) based on ground truth observations and Landsat images, evaluate the performance of this classifier when tested against new data, then deploy the classifier to perform CDBCTC change analysis of multiple locations. The proposed framework includes image calibration, support vector machine (SVM) training and tuning, statistical assessment of model accuracy, and temporal pixel-based image differencing. Validation of the methodology was performed by cross-validation and train/test split using ground truth observations of benthic cover from four different reefs. These four locations (Palmyra Atoll, Kingman Reef, Baker Island Atoll, and Howland Island) as well as two additional locations (Kiritimati Island and Tabuaeran Island) were then evaluated for CDBCTC change detection. The in-situ training accuracy against ground truth observations for Palmyra Atoll, Kingman Reef, Baker Island Atoll, and Howland Island were 87.9%, 85.7%, 69.2%, and 82.1% respectively. The classifier attained generalized accuracy scores of 78.8%, 81.0%, 65.4%, and 67.9% for the respective locations when trained using ground truth observations from neighboring reefs and tested against the local ground truth observations of each reef. The classifier was trained using the consolidated ground truth data of all four sites and attained a cross-validated accuracy of 75.3%. The CDBCTC change detection analysis showed a decrease in CDBCTC of 32% at Palmyra Atoll, 25% at Kingman Reef, 40% at Baker Island Atoll, 25% at Howland Island, 35% at Tabuaeran Island, and 43% at Kiritimati Island. This research establishes a methodology for developing a robust classifier and the associated Controlled Parameter Cross-Validation (CPCV) process for evaluating how well the model will generalize to new data. It is an important step for improving the scientific understanding of temporal change within coral reefs around the globe.

This study considers the various factors that regulate nutrients supply in the Red Sea. Multi-sensor observation and reanalysis datasets are used to examine the relationships among dust deposition, sea surface temperature (SST), and wind speed, as they may contribute to anomalous phytoplankton blooms, through time-series and correlation analyses. A positive correlation was found at 0–3 months lag between chlorophyll-a (Chl-a) anomalies and dust anomalies over the Red Sea regions. Dust deposition process was further examined with dust aerosols’ vertical distribution using satellite lidar data. Conversely, a negative correlation was found at 0–3 months lag between SST anomalies and Chl-a that was particularly strong in the southern Red Sea during summertime. The negative relationship between SST and phytoplankton is also evident in the continuously low levels of Chl-a during 2015 to 2016, which were the warmest years in the region on record. The overall positive correlation between wind speed and Chl-a relate to the nutritious water supply from the Gulf of Aden to the southern Red Sea and the vertical mixing encountered in the northern part. Ocean Color Climate Change Initiative (OC-CCI) dataset experience some temporal inconsistencies due to the inclusion of different datasets. We addressed those issues in our analysis with a valid interpretation of these complex relationships.

The Grand Ethiopian Renaissance Dam (GERD), formerly known as the Millennium Dam, has been filling at a fast rate. This project has created issues for the Nile Basin countries of Egypt, Sudan, and Ethiopia. The filling of GERD has an impact on the Nile Basin hydrology and specifically the water storages (lakes/reservoirs) and flow downstream. In this study, through the analysis of multi-source satellite imagery, we study the filling of the GERD reservoir. The time-series generated using Sentinel-1 SAR imagery displays the number of classified water pixels in the dam from early June 2017 to September 2020, indicating a contrasting trend in August and September 2020 for the upstream/downstream water bodies: upstream of the dam rises steeply, while downstream decreases. Our time-series analysis also shows the average monthly precipitation (derived using IMERG) in the Blue Nile Basin in Ethiopia has received an abnormally high amount of rainfall as well as a high amount of runoff (analyzed using GLDAS output). Simultaneously, the study also demonstrates the drying trend downstream at Lake Nasser in Southern Egypt before December 2020. From our results, we estimate that the volume of water at GERD has already increased by 3.584 billion cubic meters, which accounts for about 5.3% of its planned capacity (67.37 billion cubic meters) from 9 July–30 November 2020. Finally, we observed an increasing trend in GRACE anomalies for GERD, whereas, for the Lake Nasser, we observed a decreasing trend. In addition, our study discusses potential interactions between GERD and the rainfall and resulting flood in Sudan. Our study suggests that attention should be drawn to the connection between the GERD filling and potential drought in the downstream countries during the upcoming dry spells in the Blue Nile River Basin. This study provides an open-source technique using Google Earth Engine (GEE) to monitor the changes in water level during the filling of the GERD reservoir. GEE proves to be a powerful as well as an efficient way of analyzing computationally intensive SAR images.

In September 2015, the members of United Nations adopted the 2030 Agenda for Sustainable Development with universal applicability of 17 Sustainable Development Goals (SDGs) and 169 targets. The SDGs are consequential for the development of the countries in the Nile watershed, which are affected by water scarcity and experiencing rapid urbanization associated with population growth. Earth Observation (EO) has become an important tool to monitor the progress and implementation of specific SDG targets through its wide accessibility and global coverage. In addition, the advancement of algorithms and tools deployed in cloud computing platforms provide an equal opportunity to use EO for developing countries with limited technological capacity. This study applies EO and cloud computing in support of the SDG 6 “clean water and sanitation” and SDG 11 “sustainable cities and communities” in the seven Nile watershed countries through investigations of EO data related to indicators of water stress (Indicator 6.4.2) and urbanization and living conditions (Indicators 11.3.1 and 11.1.1), respectively. Multiple approaches including harmonic, time series and correlational analysis are used to assess and evaluate these indicators. In addition, a contemporary deep-learning classifier, fully convolution neural networks (FCNN), was trained to classify the percentage of impervious surface areas. The results show the spatial and temporal water recharge pattern among different regions in the Nile watershed, as well as the urbanization in selected cities of the region. It is noted that the classifier trained from the developed countries (i.e., the United States) is effective in identifying modern communities yet limited in monitoring rural and slum regions.

Drylands cover about 40% of the world’s land area and support two billion people, most of them living in developing countries that are at risk due to land degradation. Over the last few decades, there has been warming, with an escalation of drought and rapid population growth. This will further intensify the risk of desertification, which will seriously affect the local ecological environment, food security and people’s lives. The goal of this research is to analyze the hydrological and land cover characteristics and variability over global arid and semi-arid regions over the last decade (2010–2019) using an integrative approach of remotely sensed and physical process-based numerical modeling (e.g., Global Land Data Assimilation System (GLDAS) and Famine Early Warning Systems Network (FEWS NET) Land Data Assimilation System (FLDAS) models) data. Interaction between hydrological and ecological indicators including precipitation, evapotranspiration, surface soil moisture and vegetation indices are presented in the global four types of arid and semi-arid areas. The trends followed by precipitation, evapotranspiration and surface soil moisture over the decade are also mapped using harmonic analysis. This study also shows that some hotspots in these global drylands, which exhibit different processes of land cover change, demonstrate strong coherency with noted groundwater variations. Various types of statistical measures are computed using the satellite and model derived values over global arid and semi-arid regions. Comparisons between satellite- (NASA-USDA Surface Soil Moisture and MODIS Evapotranspiration data) and model (FLDAS and GLDAS)-derived values over arid regions (BSh, BSk, BWh and BWk) have shown the over and underestimation with low accuracy. Moreover, general consistency is apparent in most of the regions between GLDAS and FLDAS model, while a strong discrepancy is also observed in some regions, especially appearing in the Nile Basin downstream hyper-arid region. Data-driven modelling approaches are thus used to enhance the models’ performance in this region, which shows improved results in multiple statistical measures ((RMSE), bias ($\psi$), the mean absolute percentage difference ($\left|\psi \right|)$) and the linear regression coefficients (i.e., slope, intercept, and coefficient of determination (R²)).

Using new mathematical and data-driven techniques, we propose new indices to measure and predict the strength of different El Niño events and how they affect regions like the Nile River Basin (NRB). Empirical Mode Decomposition (EMD), when applied to Southern Oscillation Index (SOI), yields three Intrinsic Mode Functions (IMF) tracking recognizable and physically significant non-stationary processes. The aim is to characterize underlying signals driving ENSO as reflected in SOI, and show that those signals also meaningfully affect other physical processes with scientific and predictive utility. In the end, signals are identified which have a strong statistical relationship with various physical factors driving ENSO variation. IMF 6 is argued to track El Niño and La Niña events occurrence, while IMFs 7 and 8 represent another signal, which reflects on variations in El Niño strength and variability between events. These we represent an underlying inter-annual variation between different El Niño events. Due to the importance of the latter, IMFs 7 and 8, are defined as Interannual ENSO Variability Indices (IEVI) and referred to as IEVI α and IEVI β. EMD when applied to the NRB precipitation, affecting the Blue Nile yield, identifying the IEVI-driven IMFs, with high correlations of up to ρ = 0.864, suggesting a decadal variability within NRB that is principally driven by interannual decadal-scale variability highlighting known geographical relationships. Significant hydrological processes, driving the Blue Nile yield, are accurately identified using the IEVI as a predictor. The IEVI-based model performed significantly atp = 0.038 with Blue Nile yield observations.