Shallow-water carbonate rocks constitute a crucial component of large guyots, arising in distinct environments and harboring valuable insights into the evolutionary stages of seamount islands as well as the tectonic conditions of the underlying oceanic plate. Laser Ablation Multi-Collector Inductively Coupled Plasma Mass Spectrometry (LA-MC-ICP-MS) was used to conduct in situ U–Pb isotope dating of carbonate minerals with low uranium content collected from Weijia Guyot. This dating approach yielded crucial evidence for the vertical development of the seamount. Our study indicates that shallow-water carbonate rocks in Weijia Guyot had a temporal range between 91 My and 137 My. The carbonate rocks underwent two growth phases, Hauterivian to Barremian and Cenomanian to Turonian, with a hiatus of approximately 20 My. Since the Hauterivian age, the shield volcano of Weijia Guyot is essentially complete, with its seamount top exposed at or near sea level and receiving its first stage of shallow-water carbonate sedimentation. Based on the dating of both shallow-water carbonate rocks and hawaiite within the Weijia Guyot, it is inferred that approximately 10 My elapsed from shield-building volcanism to late alkalic volcanism. During the Turonian age, the main reason for the second phase of shallow-water carbonate rocks in the seamounts was the regional tectonic uplift triggered by the drift of the Weijia Guyot along with the Pacific Plate toward the Society hotspot.

Polymetallic nodules constitute a strategically important deep sea mineral resource enriched in nickel, cobalt, copper, and other critical metals. Accurate prediction of their spatial distribution is crucial for resource assessment and sustainable exploitation. However, sparse sampling, high survey costs, and complex nonlinear interactions among environmental factors make this task difficult. To address these challenges, this study applies a quantile regression forest to analyze the data from 233 box-core stations across a 23,000 km² area in the eastern Pacific, integrating bathymetry and backscatter intensity. Cross-validation verifies model performance. The trained model predicts nodule abundance across an adjacent 3000 km² study area and validates it against 12 independent stations that were not involved in the training. This external validation gives a root mean square error of 4.11 kg/m². The quantile regression forest model also estimates uncertainty to quantify prediction reliability. The resulting uncertainty map distinguishes high-confidence zones from areas with elevated uncertainty. In 46% of the study area, normalized uncertainty falls below 0.50, indicating higher reliability. The remaining 54% shows higher uncertainty and requires additional sampling. This method combining independent spatial validation and uncertainty visualization provides a transparent tool for deep sea mineral resource assessment where data are sparse.