Application of machine learning to map the global distribution of deep-sea sediments

2020 ◽  
Author(s):  
Markus Diesing
Keyword(s):  
Machine Learning ◽  
Deep Sea ◽  
Learning Algorithm ◽  
Predictor Variable ◽  
Global Ocean ◽  
Predictor Variables ◽  
Maximum Temperature ◽  
Sea Floor ◽  
Deep Sea Sediments ◽  
Calcareous Sediment

<p>The deep-sea floor accounts for >90% of seafloor area and >70% of the Earth’s surface. It acts as a receptor of the particle flux from the surface layers of the global ocean, is a place of biogeochemical cycling, records environmental and climate conditions through time and provides habitat for benthic organisms. Maps of the spatial patterns of deep-sea sediments are therefore a major prerequisite for many studies addressing aspects of deep-sea sedimentation, biogeochemistry, ecology and related fields.</p><p>A new digital map of deep-sea sediments of the global ocean is presented. The map was derived by applying the Random Forest machine-learning algorithm to published sample data of seafloor lithologies and environmental predictor variables. The selection of environmental predictors was initially based on the current understanding of the controls on the distribution of deep-sea sediments and the availability of data. A predictor variable selection process ensured that only important and uncorrelated variables were employed in the model. The three most important predictor variables were sea-surface maximum salinity, sea-floor maximum temperature and bathymetry. The occurrence probabilities of seven seafloor lithologies (Calcareous sediment, Clay, Diatom ooze, Lithogenous sediment, Mixed calcareous-siliceous ooze, Radiolarian ooze and Siliceous mud) were spatially predicted. The final map shows the most probable seafloor lithology and an associated probability value, which may be viewed as a spatially explicit measure of map confidence. An assessment of the accuracy of the map was based on a test set of observations not used for model training. Overall map accuracy was 69.5% (95% confidence interval: 67.9% - 71.1%). The sea-floor lithology map bears some resemblance with previously published hand-drawn maps in that the distribution of Calcareous sediment, Clay and Diatom ooze are very similar. Clear differences were however also noted: Most strikingly, the map presented here does not display a band of Radiolarian ooze in the equatorial Pacific.</p><p>The probability surfaces of individual seafloor lithologies, the categorical map of the seven mapped lithologies and the associated map confidence will be made freely available. It is hoped that they form a useful basis for research pertaining to deep-sea sediments.</p>

scholarly journals Deep-sea sediments of the global ocean

2020 ◽  
Author(s):  
Markus Diesing
Keyword(s):  
Machine Learning ◽  
Spatial Distribution ◽  
Deep Sea ◽  
Learning Algorithm ◽  
Marine Species ◽  
Global Ocean ◽  
Teaching Management ◽  
Sediment Distribution ◽  
Deep Sea Sediments ◽  
Seafloor Sediment

Abstract. Although the deep-sea floor accounts for more than 70 % of the Earth's surface, there has been little progress in relation to deriving maps of seafloor sediment distribution based on transparent, repeatable and automated methods such as machine learning. A new digital map of the spatial distribution of seafloor lithologies in the deep sea below 500 m water depth is presented to address this shortcoming. The lithology map is accompanied by estimates of the probability of the most probable class, which may be interpreted as a spatially-explicit measure of confidence in the predictions, and probabilities for the occurrence of seven lithology classes (Calcareous sediment, Clay, Diatom ooze, Lithogenous sediment, Mixed calcareous-siliceous ooze, Radiolarian ooze and Siliceous mud). These map products were derived by the application of the Random Forest machine learning algorithm to a homogenised dataset of seafloor lithology samples and global environmental predictor variables that were selected based on the current understanding of the controls on the spatial distribution of deep-sea sediments. The overall accuracy of the lithology map is 69.5 %, with 95 % confidence limits of 67.9 % and 71.1 %. It is expected that the map products are useful for various purposes including, but not limited to, teaching, management, spatial planning, design of marine protected areas and as input for global spatial predictions of marine species distributions and seafloor sediment properties. The map products are available at https://doi.org/10.1594/PANGAEA.911692 (Diesing, 2020).

scholarly journals Deep-sea sediments of the global ocean

2020 ◽  
Vol 12 (4) ◽  
pp. 3367-3381
Author(s):  
Markus Diesing
Keyword(s):  
Machine Learning ◽  
Spatial Distribution ◽  
Deep Sea ◽  
Learning Algorithm ◽  
Marine Species ◽  
Global Ocean ◽  
Teaching Management ◽  
Sediment Distribution ◽  
Deep Sea Sediments ◽  
Seafloor Sediment

Abstract. Although the deep-sea floor accounts for approximately 60 % of Earth's surface, there has been little progress in relation to deriving maps of seafloor sediment distribution based on transparent, repeatable, and automated methods such as machine learning. A new digital map of the spatial distribution of seafloor lithologies below 500 m water depth is presented to address this shortcoming. The lithology map is accompanied by estimates of the probability of the most probable class, which may be interpreted as a spatially explicit measure of confidence in the predictions, and probabilities for the occurrence of five lithology classes (calcareous sediment, clay, diatom ooze, lithogenous sediment, and radiolarian ooze). These map products were derived by the application of the random-forest machine-learning algorithm to a homogenised dataset of seafloor lithology samples and global environmental predictor variables that were selected based on the current understanding of the controls on the spatial distribution of deep-sea sediments. It is expected that the map products are useful for various purposes including, but not limited to, teaching, management, spatial planning, design of marine protected areas, and as input for global spatial predictions of marine species distributions and seafloor sediment properties. The map products are available at https://doi.org/10.1594/PANGAEA.911692 (Diesing, 2020).

scholarly journals Machine Learning Models of COVID-19 Cases in the United States: A Study of Initial Lockdown and Reopen Regimes

2021 ◽  
Vol 11 (23) ◽  
pp. 11227
Author(s):  
Arnold Kamis ◽  
Yudan Ding ◽  
Zhenzhen Qu ◽  
Chenchen Zhang
Keyword(s):  
United States ◽  
Machine Learning ◽  
Additive Model ◽  
Regression Tree ◽  
Predictor Variable ◽  
The United States ◽  
Predictor Variables ◽  
Future Research ◽  
Machine Learning Methods ◽  
Variance Explained

The purpose of this paper is to model the cases of COVID-19 in the United States from 13 March 2020 to 31 May 2020. Our novel contribution is that we have obtained highly accurate models focused on two different regimes, lockdown and reopen, modeling each regime separately. The predictor variables include aggregated individual movement as well as state population density, health rank, climate temperature, and political color. We apply a variety of machine learning methods to each regime: Multiple Regression, Ridge Regression, Elastic Net Regression, Generalized Additive Model, Gradient Boosted Machine, Regression Tree, Neural Network, and Random Forest. We discover that Gradient Boosted Machines are the most accurate in both regimes. The best models achieve a variance explained of 95.2% in the lockdown regime and 99.2% in the reopen regime. We describe the influence of the predictor variables as they change from regime to regime. Notably, we identify individual person movement, as tracked by GPS data, to be an important predictor variable. We conclude that government lockdowns are an extremely important de-densification strategy. Implications and questions for future research are discussed.

Clay mineral distribution related to rift activity, sea-level changes and paleoceanography in the Cretaceous of the Atlantic Ocean

Clay Minerals ◽  
1993 ◽  
Vol 28 (1) ◽  
pp. 61-84 ◽  
Author(s):  
M. Thiry ◽  
T. Jacquin
Keyword(s):  
Atlantic Ocean ◽  
Sea Level ◽  
Clay Minerals ◽  
Clay Mineral ◽  
Deep Sea ◽  
Depositional Environments ◽  
Sea Level Changes ◽  
Sea Floor ◽  
Deep Sea Sediments ◽  
Bottom Waters

AbstractThe distribution of clay minerals from the N and S Atlantic Cretaceous deep-sea sediments is related to rifting, sea-floor spreading, sea-level variations and paleoceanography. Four main clay mineral suites were identified: two are inherited and indicative of ocean geodynamics, whereas the others result from transformation and authigenesis and are diagnostic of Cretaceous oceanic depositional environments. Illite and chlorite, together with interstratified illite-smectite and smectite occur above the sea-floor basalts and illustrate the contribution of volcanoclastic materials of basaltic origin to the sediments. Kaolinite, with variable amounts of illite, chlorite, smectite and interstratified minerals, indicates detrital inputs from continents near the platform margins. Kaolinite decreases upward in the series due to open marine environments and basin deepening. It may increase in volume during specific time intervals corresponding to periods of falling sea-level during which overall facies regression and erosion of the surrounding platforms occurred. Smectite is the most abundant clay mineral in the Cretaceous deep-sea sediments. Smectite-rich deposits correlate with periods of relatively low sedimentation rates. As paleoweathering profiles and basal deposits at the bottom of Cretaceous transgressive formations are mostly kaolinitic, smectite cannot have been inherited from the continents. Smectite is therefore believed to have formed in the ocean by transformation and recrystallization of detrital materials during early diagenesis. Because of the slow rate of silicate reactions, transformation of clay minerals requires a long residence time of the particles at the water/sediment interface; this explains the relationships between the observed increases in smectite with long-term sea-level rises that tend to starve the basinal settings of sedimentation. Palygorskite, along with dolomite, is relatively common in the N and S Atlantic Cretaceous sediments. It is not detrital because correlative shelf deposits are devoid of palygorskite. Palygorskite is diagnostic of Mg-rich environments and is indicative of the warm and hypersaline bottom waters of the Cretaceous Atlantic ocean.

Is Infidelity Predictable? Using Interpretable Machine Learning to Identify the Most Important Predictors of Infidelity

2020 ◽  
Author(s):  
Laura Marika Vowels ◽  
Matthew J Vowels ◽  
Kristen P Mark
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Large Body ◽  
Predictor Variable ◽  
Well Being ◽  
Relationship Length ◽  
Three Samples ◽  
Online Infidelity ◽  
Shapley Values ◽  
Game Theoretic

Infidelity is a common occurrence in relationships and can have a devastating impact on both partners’ well-being. A large body of literature have attempted to factors that can explain or predict infidelity but have been unable to estimate the relative importance of each predictor. We used a machine learning algorithm, random forest (a type of interpretable highly non-linear decision tree), to predict in-person and online infidelity and intentions toward future infidelity across three samples (two dyadic samples; N = 1846). We also used a game theoretic explanation technique, Shapley values, which allowed us to estimate the effect size of each predictor variable on infidelity. The present study showed that infidelity was somewhat predictable overall with interpersonal factors (relationship satisfaction, love, desire, relationship length) being the most predictive. The results suggest that addressing relationship difficulties early in the relationship can help prevent future infidelity.

Uncovering the Most Important Factors for Predicting Sexual Desire using Interpretable Machine Learning

2020 ◽  
Author(s):  
Laura Marika Vowels ◽  
Matthew J Vowels ◽  
Kristen P Mark
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Sexual Desire ◽  
Learning Algorithm ◽  
Predictor Variable ◽  
Machine Learning Algorithm ◽  
Societal Factors ◽  
Interpretable Machine Learning ◽  
Several Variables ◽  
Two Samples

Previous studies have found a number of individual, relational, and societal factors that are associated with sexual desire. However, no studies to date have examined which of these variables are the most predictive of sexual desire. We used a machine learning algorithm, random forest (a type of interpretable highly non-linear decision tree), to predict sexual desire from a large number of predictors across two samples (N = 1846; includes 754 individuals forming 377 couples). We also used a Shapley value technique to estimate the size and direction of the effect of each predictor variable on the model outcome. The model predicted around 40% of variance in dyadic and solitary desire with women’s desire being more predictable than men’s. Several variables consistently predicted sexual desire including individual, relational, and societal factors. The study provides the strongest evidence to date of the most important predictors for dyadic and solitary desire.

Identifying key drivers of peat-fires across Kalimantan’s ex‑Mega Rice Project area using machine learning

2021 ◽  
Author(s):  
Alexander Horton ◽  
Vili Virkki ◽  
Anu Lounela ◽  
Jukka Miettinen ◽  
Matti Kummu
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Full Range ◽  
Local Population ◽  
Vegetation Indices ◽  
Predictor Variable ◽  
Driving Factors ◽  
Predictor Variables ◽  
Entire Study ◽  
Burnt Areas

<p>Throughout Indonesia - ecological degradation, agricultural expansion, and the digging of draining canals has compromised the integrity and functioning of large swathes of peatland forest, leaving behind a fragmented landscape of scrubland, successional forest, and newly established plantations. These landscapes are susceptible to extensive and intensive wildfires that rage out of control each year. One of the most affected regions is the ex-Mega Rice Project (EMRP) area in Central Kalimantan on the island of Borneo, where 1 million ha of peatland forest were cleared and 4000 km of canals were dug between 1996-1998, in an attempt to initiate large scale industrial rice cultivation. This led to disturbances to the underlying hydrology, the local ecology, and the ability of the local population to maintain a livelihood, who’s efforts are thwarted each year but the returning wildfires.</p><p>Directing  fire prevention and mitigation efforts requires a detailed understanding of the main drivers of fire distribution and the conditions of initiation. To this end, we have developed a fire susceptibility model using machine learning (XGBoost random forest) that characterises the relationships between key predictor variables and the distribution of historic fire locations. Using the model, we determine the relative importance of each predictor variable in controlling the initiation and spread of fires. We included land-cover classifications, a forest clearance index, vegetation indices , drought indexes, distances to infrastructure , topography, and peat depth, as well as the Oceanic Niño Index (ONI). The model was trained to separate burnt areas from not burnt areas using point samples of predictor variables taken from both, and then tested by applying the model across the entire study area for all years. The model performance consistently scores highly in both accuracy and precision across all years (>0.75 and >0.68 respectively), though recall metrics are much lower (>0.25).</p><p>Our results confirm the anthropogenic dependence of extreme fire events in the region, with the distance to settlements, and distance to canals consistently weighted as some of the most important driving factors within the model structure. In combination, the vegetation indices were the strongest indicators of fire prevalence. Ours is the first analysis in the region to encompass the full range of driving factors within a single model that captures the inter-annual variation as well as the spatial distribution of peatland fires. Our results can be used to target the root causes of fire initiation and propagation to better construct regulation and rehabilitation efforts to mitigate future wildfires.</p>

scholarly journals Changes in Ocean Ventilation Rates Over the Last 7000 Years Based on 14C Variations in the Atmosphere and Oceans

Radiocarbon ◽  
1989 ◽  
Vol 31 (03) ◽  
pp. 481-492 ◽  
Author(s):  
T-H Peng
Keyword(s):  
Age Differences ◽  
Benthic Foraminifera ◽  
Deep Sea ◽  
Ventilation Rate ◽  
Global Ocean ◽  
Production Rates ◽  
The Past ◽  
Ocean Ventilation ◽  
Deep Sea Sediments ◽  
Ventilation Rates

Changes in the ocean ventilation rate may be one of the causes for a net decrease of 100‰ Δ 14C in atmospheric CO2 over the last 8000 years. Ocean ventilation rates of the past can be derived from the 14C record preserved in planktonic and benthic foraminifera in deep-sea sediments. Results of 14C dating using accelerator mass spectrometry on deep sea sediments from the South China Sea show that the age differences between planktonic (G sacculifer) and benthic foraminifera increase from 1350 yr ca 7000 yr ago to 1590 yr at present. An 11-box geochemical model of global ocean circulation was used for this study. Both tree-ring-determined atmospheric 14C values and foraminifera 14C age differences are used as constraints to place limits on patterns of changes in ocean ventilation rates and in atmospheric 14C production rates. Results indicate: 1) 14C production rates in the atmosphere may have decreased by as much as 30% between 7000 and 3000 yr ago, and may have increased again by ca 15% in the past 2000 yr, and 2) the global ocean ventilation rate may not have been at steady state over the last 7000 yr, but may have slowed by as much as 35%.

Sign in / Sign up

Export Citation Format

Share Document