In Africa, several new seaport developments are being considered. In sedimentary environments, such port developments can have adverse impacts on the evolution of adjacent coastlines. To learn from past port engineering practice, we created a unique database containing the coastline evolution and characteristics of 130 existing African seaports. Whereas the systematic mapping of coastal impacts was previously hampered by data availability, innovative automated satellite image processing techniques have enabled us to intercompare ports at an unprecedented continental scale. We found large geographical differences with respect to the beach evolution. The total detected changes in the beach area between 1984 and 2018 totaled 44 km², of which ca. 23 km² is accretion and ca. 21 km² is erosion. The top 10% “hotspot” ports account for more than 65% of these changes. These hotspots exhibit common characteristics, namely: they are located on open coastlines, have large alongshore sediment transport potential, and have large cross-shore breakwaters. Although these driving characteristics are well established in coastal engineering theory, our results indicate that the beaches adjacent to the existing seaports have been and remain seriously affected by these drivers. Our results can be used to inform beach maintenance strategies for existing seaports and to support planners and engineers to minimize long-term coastal impacts of port expansions and new port developments in Africa in the future.

Robust predictions of shoreline change are critical for sustainable coastal management. Despite advancements in shoreline models, objective benchmarking remains limited. Here we present results from ShoreShop2.0, an international collaborative benchmarking workshop, where 34 groups submitted shoreline change predictions in a blind competition. Subsets of shoreline observations at an undisclosed site (BeachX) over short (5-year) and medium (50-year) periods were withheld from modelers and used for model benchmarking. Using satellite-derived shoreline datasets for calibration and evaluation, the best performing models achieved prediction accuracies on the order of 10 m, comparable to the accuracy of the satellite shoreline data, indicating that certain beaches can be modelled nearly as well as they can be remotely observed. The outcomes from this collaborative benchmarking competition critically review the present state-of-the-art in shoreline change prediction as well as reveal model limitations, facilitate improvements, and offer insights for advancing shoreline-prediction capabilities.

Evaluating shoreline retreat rate (SRR) on different spatial‐temporal scales is critical for effective coastal management. Large‐scale evaluations typically rely on data‐driven methods such as Discrete Bayesian networks (BNs). However, these BNs require discretization of continuous variables which can lead to information loss. Here, we propose a new method, the Hybrid BN to incorporate continuous variables without discretization. Both Discrete and Hybrid BNs were developed and compared to evaluate large‐scale (continental scale) SRR in Australia, using Digital Earth Australia data set. These BNs used forcing parameters (e.g., waves, tide, sediment sink/source, and sea level rise [SLR]) and geomorphic settings (e.g., geomorphology, backshore profile, and surfzone slope) to predict SRR. Validation of the BNs showed that Hybrid BNs, which provide a more realistic assessment of the range of SRR, outperform in predicting continuous variables, when compared with Discrete BNs. However, Discrete and Hybrid BNs provide consistent qualitative findings for the SRR of Australia. Among forcing parameters, the sediment sink/source was found to be the most informative variable to indicate the shoreline retreat, followed by tide, SLR rate, and wave processes. In the scenario of an increased SLR rate, tropical tidal flats were predicted as the most at risk coasts in Australia. We found that BNs can reflect the impact of different factors on coastal evolution, and predict future shoreline change by exploring historical data. The performance of these models can be further improved when more data sets become available.

Livestock grazing is a major land use in the Great Barrier Reef Catchment Area (GBRCA). Heightened grazing density coupled with inadequate land management leads to accelerated soil erosion and increased sediment loads being transported downstream. Ultimately, these increased sediment loads impact the water quality of the Great Barrier Reef (GBR) lagoon. Ground cover mapping has been adopted to monitor and assess the land condition in the GBRCA. However, accurate prediction of ground cover remains a vital knowledge gap to inform proactive approaches for improving land conditions. Herein, we explored two deep learning-based spatio-temporal prediction models, including convolutional LSTM (ConvLSTM) and Predictive Recurrent Neural Network (PredRNN), to predict future ground cover. The two models were evaluated on different spatial scales, ranging from a small site (i.e., <5 km²) to the entire GBRCA, with different quantities of training data. Following comparisons against 25% withheld testing data, we found the following: (1) both ConvLSTM and PredRNN accurately predicted the next-season ground cover for not only a single site but also the entire GBRCA. They achieved this with a Mean Absolute Error (MAE) under 5% and a Structural Similarity Index Measure (SSIM) exceeding 0.65; (2) PredRNN superseded ConvLSTM by providing more accurate next-season predictions with better training efficiency; (3) The accuracy of PredRNN varies seasonally and spatially, with lower accuracy observed for low ground cover, which is underestimated. The models assessed in this study can serve as an early-alert tool to produce high-accuracy and high-resolution ground cover prediction one season earlier than observation for the entire GBRCA, which enables local authorities and grazing property owners to take preventive measures to improve land conditions. This study also offers a new perspective on the future utilization of predictive spatio-temporal models, particularly over large spatial scales and across varying environmental sites.