A deep-sea (4500 m) trial of a pre-prototype polymetallic nodule collector with independent scientific monitoring revealed that a gravity current formed behind the collector channeled through steeper seafloor sections and traveled 500 m downslope. The prevailing bottom currents dominated sediment dispersion up to the end of the monitoring area at 4.5 km distance. The maximum suspended particle concentration recorded 50 m from mining lanes was up to four orders of magnitude higher than ambient values but decreased rapidly with increasing time, distance, and altitude. Most of the plume remained close to the seafloor, with the highest concentrations at 1 m monitoring altitude and reaching background concentrations at 50 m. Rapid particle flocculation was followed by fast and substantial sediment redeposition. A mm-scale photogrammetric seafloor reconstruction allowed quantitative estimates of the thickness of redeposited sediment next to mining lanes of ≈ 3 cm and a minimum erosional depth of 5 cm.

In this study, high-resolution bathymetric multibeam and optical image data, both obtained within the Belgian manganese (Mn) nodule mining license area by the autonomous underwater vehicle (AUV) Abyss, were combined in order to create a predictive random forests (RF) machine learning model. AUV bathymetry reveals small-scale terrain variations, allowing slope estimations and calculation of bathymetric derivatives such as slope, curvature, and ruggedness. Optical AUV imagery provides quantitative information regarding the distribution (number and median size) of Mn nodules. Within the area considered in this study, Mn nodules show a heterogeneous and spatially clustered pattern, and their number per square meter is negatively correlated with their median size. A prediction of the number of Mn nodules was achieved by combining information derived from the acoustic and optical data using a RF model. This model was tuned by examining the influence of the training set size, the number of growing trees (ntree), and the number of predictor variables to be randomly selected at each node (mtry) on the RF prediction accuracy. The use of larger training data sets with higher ntree and mtry values increases the accuracy. To estimate the Mn-nodule abundance, these predictions were linked to ground-truth data acquired by box coring. Linking optical and hydroacoustic data revealed a nonlinear relationship between the Mn-nodule distribution and topographic characteristics. This highlights the importance of a detailed terrain reconstruction for a predictive modeling of Mn-nodule abundance. In addition, this study underlines the necessity of a sufficient spatial distribution of the optical data to provide reliable modeling input for the RF.

Machine learning spatial modeling is used for mapping the distribution of deep-sea polymetallic nodules (PMN). However, the presence and influence of spatial autocorrelation (SAC) have not been extensively studied. SAC can provide information regarding the variable selection before modeling, and it results in erroneous validation performance when ignored. ML models are also problematic when applied in areas far away from the initial training locations, especially if the (new) area to be predicted covers another feature space. Here, we study the spatial distribution of PMN in a geomorphologically heterogeneous area of the Peru Basin, where SAC of PMN exists. The local Moran’s I analysis showed that there are areas with a significantly higher or lower number of PMN, associated with different backscatter values, aspect orientation, and seafloor geomorphological characteristics. A quantile regression forests (QRF) model is used using three cross-validation (CV) techniques (random-, spatial-, and cluster-blocking). We used the recently proposed “Area of Applicability” method to quantify the geographical areas where feature space extrapolation occurs. The results show that QRF predicts well in morphologically similar areas, with spatial block cross-validation being the least unbiased method. Conversely, random-CV overestimates the prediction performance. Under new conditions, the model transferability is reduced even on local scales, highlighting the need for spatial model-based dissimilarity analysis and transferability assessment in new areas.

High-resolution mapping of deep-sea polymetallic nodules is needed (a) to understand the reasons behind their patchy distribution, (b) to associate nodule coverage with benthic fauna occurrences, and (c) to enable an accurate resource estimation and mining path planning. This study used an autonomous underwater vehicle to map 37 km² of a geomorphologically complex site in the Eastern Clarion–Clipperton Fracture Zone. A multibeam echosounder system (MBES) at 400 kHz and a side scan sonar at 230 kHz were used to investigate the nodule backscatter response. More than 30,000 seafloor images were analyzed to obtain the nodule coverage and train five machine learning (ML) algorithms: generalized linear models, generalized additive models, support vector machines, random forests (RFs) and neural networks (NNs). All models ML yielded similar maps of nodule coverage with differences occurring in the range of predicted values, particularly at parts with irregular topography. RFs had the best fit and NNs had the worst spatial transferability. Attention was given to the interpretability of model outputs using variable importance ranking across all models, partial dependence plots and domain knowledge. The nodule coverage is higher on relatively flat seafloor ( < 3°) with eastward-facing slopes. The most important predictor was the MBES backscatter, particularly from incident angles between 25 and 55°. Bathymetry, slope, and slope orientation were important geomorphological predictors. For the first time, at a water depth of 4500 m, orthophoto-mosaics and image-derived digital elevation models with 2-mm and 5-mm spatial resolutions supported the geomorphological analysis, interpretation of polymetallic nodules occurrences, and backscatter response.

Using observational data, satellite altimeters, and reanalysis model products, we have investigated eddy-induced seawater anomalies and heat and salt transport in the northeastern tropical Pacific Ocean. An eddy detection algorithm (EDA) was used to identify eddy formation at the Mexican Tehuantepec Gulf (TT) in July 2018 during an unusually strong summer wind event. The eddy separated from the coast with a mean translation velocity of 11 cm s⁻¹ and a mean radius of 115 km and traveled 2050–2400 km westwards off the Central American coast, where it was followed at approx 114^∘ W and 11^∘ N for oceanographic observation between April and May 2019. The in situ observations show that the major eddy impacts are restricted to the upper 300 m of the water column and are traceable down to 1500 m water depth. In the eddy core at 92 m water depth an extreme positive temperature anomaly of 8.2 ^∘C, a negative salinity anomaly of −0.78 psu, a positive fluorescence anomaly of +0.8 mg m⁻³, and a positive dissolved oxygen concentration anomaly of 137 µmol kg⁻¹ are observed. Compared with annual climatological averages in 2018, the water trapped within the eddy is estimated to transport an average positive westward zonal heat anomaly of 85×10¹² W and an average westward negative salt anomaly of $-\mathrm{2.1}\times {\mathrm{10}}^{\mathrm{6}}$ kg s⁻¹. The heat transport is the equivalent of 1 % of the total annual zonal eddy-induced heat transport at this latitude in the Pacific Ocean. Understanding the dynamics of long-lived mesoscale eddies that may reach the seafloor in this region of the Pacific Ocean is especially important in light of potential deep-sea mining activities that are being targeted on this area.

Using observational data, satellite altimeters, and reanalysis model products, we have investigated eddy-induced seawater anomalies and heat/salt transport in the northeastern tropical Pacific Ocean. An eddy detection algorithm (EDA) was used to identify eddy formation at the Mexican Tehuantepec Gulf (TT) in July 2018 during an unusually strong summer wind event. The eddy separated from the coast with a mean translation velocity of 11 cm s^-1 and a mean radius of 115 km and travelled 2050–2400 km westwards off the Central American coast, where it was followed at approx -114° W and 11° N for oceanographic observation between April and May 2019. The in-situ observations show that the major eddy impacts are restricted to the upper 300 m of the water column and are traceable down to 1500 m water depth. In the eddy core at 80 m water depth an extreme positive temperature anomaly of +8 °C, a negative salinity anomaly of -0.75 psu, a positive fluorescence anomaly of +0.8 mg m^-3 and a positive dissolved oxygen concentration anomaly of 160 µmol kg^-1 are observed. Considering the water volume trapped within the eddy, an average positive westward zonal heat transport anomaly of 85 × 10¹² W and an average westward negative zonal salt transport of -2.2 × 10⁶ kg s^-1 are estimated. The heat transport is the equivalent of 1 % of the total annual zonal eddy-induced heat transport at this latitude in the Pacific Ocean. Understanding the dynamics of mesoscale eddies in this region of the Pacific Ocean is especially important in the light of potential deep-sea mining activities that are being targeted on this area.