The primary objective of this study was to predict the distribution of mesophotic hard corals in the Au‘au Channel in the Main Hawaiian Islands (MHI). Mesophotic hard corals are light-dependent corals adapted to the low light conditions at approximately 30 to 150 m in depth. Several physical factors potentially influence their spatial distribution, including aragonite saturation, alkalinity, pH, currents, water temperature, hard substrate availability and the availability of light at depth. Mesophotic corals and mesophotic coral ecosystems (MCEs) have increasingly been the subject of scientific study because they are being threatened by a growing number of anthropogenic stressors. They are the focus of this spatial modeling effort because the Hawaiian Islands Humpback Whale National Marine Sanctuary (HIHWNMS) is exploring the expansion of its scope—beyond the protection of the North Pacific Humpback Whale (Megaptera novaeangliae)—to include the conservation and management of these ecosystem components. The present study helps to address this need by examining the distribution of mesophotic corals in the Au‘au Channel region. This area is located between the islands of Maui, Lanai, Molokai and Kahoolawe, and includes parts of the Kealaikahiki, Alalākeiki and Kalohi Channels. It is unique, not only in terms of its geology, but also in terms of its physical oceanography and local weather patterns. Several physical conditions make it an ideal place for mesophotic hard corals, including consistently good water quality and clarity because it is flushed by tidal currents semi-diurnally; it has low amounts of rainfall and sediment run-off from the nearby land; and it is largely protected from seasonally strong wind and wave energy. Combined, these oceanographic and weather conditions create patches of comparatively warm, calm, clear waters that remain relatively stable through time. Freely available Maximum Entropy modeling software (MaxEnt 3.3.3e) was used to create four separate maps of predicted habitat suitability for: (1) all mesophotic hard corals combined, (2) Leptoseris, (3) Montipora and (4) Porites genera. MaxEnt works by analyzing the distribution of environmental variables where species are present, so it can find other areas that meet all of the same environmental constraints. Several steps (Figure 0.1) were required to produce and validate four ensemble predictive models (i.e., models with 10 replicates each). Approximately 2,000 georeferenced records containing information about mesophotic coral occurrence and 34 environmental predictors describing the seafloor’s depth, vertical structure, available light, surface temperature, currents and distance from shoreline at three spatial scales were used to train MaxEnt. Fifty percent of the 1,989 records were randomly chosen and set aside to assess each model replicate’s performance using Receiver Operating Characteristic (ROC), Area Under the Curve (AUC) values. An additional 1,646 records were also randomly chosen and set aside to independently assess the predictive accuracy of the four ensemble models. Suitability thresholds for these models (denoting where corals were predicted to be present/absent) were chosen by finding where the maximum number of correctly predicted presence and absence records intersected on each ROC curve. Permutation importance and jackknife analysis were used to quantify the contribution of each environmental variable to the four ensemble models. The average test AUCs for the all hard coral, Montipora, Porites and Leptoseris models were between 0.90 and 0.97, indicating ‘excellent’ overall model performance. Habitat suitability thresholds were set to 25%, 15%, 7% and 20% (i.e., the logistic output value x 100%) for the all hard coral, Montipora, Porites and Leptoseris models, respec tively. These numbers denote how suitable a location is for mesophotic corals. Predictive accuracies (measured at these suitability thresholds) were 73.1% overall for all hard corals, and using absences only, were 86.1% for Mon- tipora, 85.3% for Porites and 78.2% for Leptoseris. Permutation importance and jackknife analysis revealed that several environmental variables were important to all four of the ensemble models. These variables included depth, distance from shore, mean euphotic depth, and variance of euphotic depth. Unlike the other models, seafloor com plexity (i.e., slope of slope) was also important to the development of the Leptoseris ensemble model. While it is likely that these variables are proxies for other variables, suitable environmental conditions for mesophotic corals were highest in a broad region in the south and eastern half of the Au‘au Channel. For all hard corals and Monti- pora, predicted suitable conditions were the highest between Lahaina Roads Basin and Papawai Point. This area is characterized by relatively warmer (at the surface), moderately deep and less turbid waters than elsewhere in the study area, suggesting that these two groups prefer moderately deep waters that remain optically clear and stable through time. For Porites, suitable conditions were highest between Hanakaoo Point and Hekili Point. This area is characterized by relatively warmer, slightly shallower and less turbid waters than found in other parts of the study area, suggesting Porites prefers shallower waters and can tolerate slightly more turbid waters than either Montipora or all hard corals combined. Lastly for Leptoseris, suitable environmental conditions were highest offshore of Hekili Point, which has the deepest and most consistently warm and clear waters compared to any other part of the study area. These trends suggest that Leptoseris prefers slightly deeper, substantially less turbid and less variable waters (in terms of turbidity) than Montipora, Porites and all hard corals combined. Results from this study can be used for a number of management applications, including identifying large areas of high suitability by coral genus; delineating subzones within the sanctuary if special regulations are needed to protect MCEs; and targeting and promoting research and educational activities about these important and rare habitats. These predictive maps may also be overlaid with additional spatial information (e.g., human activities) to evaluate options for minimizing conflicts in areas with many overlapping resources and uses. However before each application, extreme care should be taken when selecting a habitat suitability threshold because it affects the probability of correctly identifying the presence and absence of mesophotic corals. In some cases, it may be more important to correctly identify locations of mesophotic coral presence (e.g., research), while in others, it may be more important to correctly identify absences (e.g., undersea cable routing). While these models help to fill some knowledge gaps about the distribution of MCEs in the Au‘au Channel Region, several data and informational gaps still exist and need to be addressed in the future. These gaps are not unique to the Au‘au Channel, as similar gaps exist across the MHI as a whole. To fill some of these gaps, future efforts should focus on developing a systematic sampling plan for mesophotic corals around each of the MHI. Systematic sampling would allow this or similar approaches to be applied to other areas in the MHI, supporting the marine spatial planning needs of the broader ocean community. Establishing a baseline for MCE distributions in the MHI is also critical because it will allow scientists and resource managers to better understand how MCEs are responding to local environmental variations and global climate changes in the future.