Exploring the Application of Machine Learning for Downscaling Climate Projections

2020 ◽  
pp. 1-17
Author(s):  
Kristin Van Abel ◽  
Amanda Back ◽  
M. Kathleen Brennan ◽  
Oriana S. Chegwidden ◽  
Mimi Hughes ◽  
...  
Keyword(s):  
Machine Learning ◽  
Climate Projections

scholarly journals Constraining uncertainty in projected gross primary production with machine learning

2020 ◽  
Author(s):  
Manuel Schlund ◽  
Veronika Eyring ◽  
Gustau Camps-Valls ◽  
Pierre Friedlingstein ◽  
Pierre Gentine ◽  
...  
Keyword(s):  
Machine Learning ◽  
Carbon Cycle ◽  
Primary Production ◽  
Carbon Sink ◽  
Gross Primary Production ◽  
Boosted Regression Trees ◽  
Supervised Machine Learning ◽  
Climate Projections ◽  
Intergovernmental Panel ◽  
The Future

<p>By absorbing about one quarter of the total anthropogenic CO<sub>2</sub> emissions, the terrestrial biosphere is an important carbon sink of Earth’s carbon cycle. A key metric of this process is the terrestrial gross primary production (GPP), which describes the biogeochemical production of energy by photosynthesis. Elevated atmospheric CO<sub>2</sub> concentrations will increase GPP in the future (CO<sub>2</sub> fertilization effect). However, projections from different Earth system models participating in the Coupled Model Intercomparison Project Phase 5 (CMIP5) show a large spread in carbon cycle related quantities. In this study, we present a new supervised machine learning approach to constrain multi-model climate projections using observation-driven data. Our method based on Gradient Boosted Regression Trees handles multiple predictor variables of the present-day climate and accounts for non-linear dependencies. Applied to GPP in the representative concentration pathway RCP 8.5 at the end of the 21st century (2081–2100), the new approach reduces the “likely” range (as defined by the Intergovernmental Panel on Climate Change) of the CMIP5 multi-model projection of GPP to 161–203 GtC yr<sup>-1</sup>. Compared to the unweighted multi-model mean (148–224 GtC yr<sup>-1</sup>), this is an uncertainty reduction of 45%. Our new method is not limited to projections of the future carbon cycle, but can be applied to any target variable where suitable gridded data is available.</p>

scholarly journals Forecasting Spatio-Temporal Dynamics on the Land Surface Using Earth Observation Data—A Review

2020 ◽  
Vol 12 (21) ◽  
pp. 3513
Author(s):  
Jonas Koehler ◽  
Claudia Kuenzer
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Time Series ◽  
Land Surface ◽  
Input Data ◽  
Earth Observation ◽  
Series Data ◽  
Climate Projections ◽  
Auto Regressive ◽  
Spatio Temporal

Reliable forecasts on the impacts of global change on the land surface are vital to inform the actions of policy and decision makers to mitigate consequences and secure livelihoods. Geospatial Earth Observation (EO) data from remote sensing satellites has been collected continuously for 40 years and has the potential to facilitate the spatio-temporal forecasting of land surface dynamics. In this review we compiled 143 papers on EO-based forecasting of all aspects of the land surface published in 16 high-ranking remote sensing journals within the past decade. We analyzed the literature regarding research focus, the spatial scope of the study, the forecasting method applied, as well as the temporal and technical properties of the input data. We categorized the identified forecasting methods according to their temporal forecasting mechanism and the type of input data. Time-lagged regressions which are predominantly used for crop yield forecasting and approaches based on Markov Chains for future land use and land cover simulation are the most established methods. The use of external climate projections allows the forecasting of numerical land surface parameters up to one hundred years into the future, while auto-regressive time series modeling can account for intra-annual variances. Machine learning methods have been increasingly used in all categories and multivariate modeling that integrates multiple data sources appears to be more popular than univariate auto-regressive modeling despite the availability of continuously expanding time series data. Regardless of the method, reliable EO-based forecasting requires high-level remote sensing data products and the resulting computational demand appears to be the main reason that most forecasts are conducted only on a local scale. In the upcoming years, however, we expect this to change with further advances in the field of machine learning, the publication of new global datasets, and the further establishment of cloud computing for data processing.

scholarly journals Reverse engineering model structures for soil and ecosystem respiration: the potential of gene expression programming

2017 ◽  
Vol 10 (9) ◽  
pp. 3519-3545 ◽  
Author(s):  
Iulia Ilie ◽  
Peter Dittrich ◽  
Nuno Carvalhais ◽  
Martin Jung ◽  
Andreas Heinemeyer ◽  
...  
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
Ecosystem Respiration ◽  
Gene Expression Programming ◽  
Carbon Assimilation ◽  
Water Dynamics ◽  
Support Vector ◽  
Climate Projections ◽  
Suitable Model ◽  
Model Structures

Abstract. Accurate model representation of land–atmosphere carbon fluxes is essential for climate projections. However, the exact responses of carbon cycle processes to climatic drivers often remain uncertain. Presently, knowledge derived from experiments, complemented by a steadily evolving body of mechanistic theory, provides the main basis for developing such models. The strongly increasing availability of measurements may facilitate new ways of identifying suitable model structures using machine learning. Here, we explore the potential of gene expression programming (GEP) to derive relevant model formulations based solely on the signals present in data by automatically applying various mathematical transformations to potential predictors and repeatedly evolving the resulting model structures. In contrast to most other machine learning regression techniques, the GEP approach generates readable models that allow for prediction and possibly for interpretation. Our study is based on two cases: artificially generated data and real observations. Simulations based on artificial data show that GEP is successful in identifying prescribed functions, with the prediction capacity of the models comparable to four state-of-the-art machine learning methods (random forests, support vector machines, artificial neural networks, and kernel ridge regressions). Based on real observations we explore the responses of the different components of terrestrial respiration at an oak forest in south-eastern England. We find that the GEP-retrieved models are often better in prediction than some established respiration models. Based on their structures, we find previously unconsidered exponential dependencies of respiration on seasonal ecosystem carbon assimilation and water dynamics. We noticed that the GEP models are only partly portable across respiration components, the identification of a general terrestrial respiration model possibly prevented by equifinality issues. Overall, GEP is a promising tool for uncovering new model structures for terrestrial ecology in the data-rich era, complementing more traditional modelling approaches.

scholarly journals Machine Learning for Conservation Planning in a Changing Climate

2020 ◽  
Vol 12 (18) ◽  
pp. 7657
Author(s):  
Ana Cristina Mosebo Fernandes ◽  
Rebeca Quintero Gonzalez ◽  
Marie Ann Lenihan-Clarke ◽  
Ezra Francis Leslie Trotter ◽  
Jamal Jokar Arsanjani
Keyword(s):  
Climate Change ◽  
Machine Learning ◽  
Machine Learning Algorithms ◽  
Climate Projections ◽  
Sage Grouse ◽  
Climate Conditions ◽  
Fragmented Habitat ◽  
Related Data ◽  
Temperature And Precipitation ◽  
Methodical Approach

Wildlife species’ habitats throughout North America are subject to direct and indirect consequences of climate change. Vulnerability assessments for the Intermountain West regard wildlife and vegetation and their disturbance as two key resource areas in terms of ecosystems when considering climate change issues. Despite the adaptability potential of certain wildlife, increased temperature estimates of 1.67–2 °C by 2050 increase the likelihood and severity of droughts, floods, heatwaves and wildfires in Utah. As a consequence, resilient flora and fauna could be displaced. The aim of this study was to locate areas of habitat for an exemplary species, i.e., sage-grouse, based on current climate conditions and pinpoint areas of future habitat based on climate projections. The locations of wildlife were collected from Volunteered Geographic Information (VGI) observations in addition to normal temperature and precipitation, vegetation cover and other ecosystem-related data. Four machine learning algorithms were then used to locate the current sites of wildlife habitats and predict suitable future sites where wildlife would likely relocate to, dependent on the effects of climate change and based on a timeframe of scientifically backed temperature-increase estimates. Our findings show that Random Forest outperforms other competing models, with an accuracy of 0.897, and a sensitivity and specificity of 0.917 and 0.885, respectively, and has great potential in Species Distribution Modeling (SDM), which can provide useful insights into habitat predictions. Based on this model, our predictions show that sage-grouse habitats in Utah will continue to decrease over the coming years due to climate change, producing a highly fragmented habitat and causing a loss of close to 70% of their current habitat. Priority Areas of Conservation (PACs) and protected areas might be deemed insufficient to halt this habitat loss, and more effort should be put into maintaining connectivity between patches to ensure the movement and genetic diversity within the sage-grouse population. The underlying data-driven methodical approach of this study could be useful for environmentalists, researchers, decision-makers, and policymakers, among others.

scholarly journals Reverse engineering model structures for soil and ecosystem respiration: the potential of gene expression programming

2016 ◽  
Author(s):  
Iulia Ilie ◽  
Peter Dittrich ◽  
Nuno Carvalhais ◽  
Martin Jung ◽  
Andreas Heinemeyer ◽  
...  
Keyword(s):  
Gene Expression ◽  
Machine Learning ◽  
Ecosystem Respiration ◽  
Traditional Approach ◽  
Gene Expression Programming ◽  
Water Dynamics ◽  
Support Vector ◽  
Climate Projections ◽  
Suitable Model ◽  
Model Structures

Abstract. Accurate modelling of land-atmosphere carbon fluxes is essential for future climate projections. However, the exact responses of carbon cycle processes to climatic drivers often remain uncertain. Presently, knowledge derived from experiments complemented with a steadily evolving body of mechanistic theory provides the main basis for developing the respective models. The strongly increasing availability of measurements may complicate the traditional hypothesis driven path to developing mechanistic models, but it may facilitate new ways of identifying suitable model structures using machine learning as well. Here we explore the potential to derive model formulations automatically from data based on gene expression programming (GEP). GEP automatically (re)combines various mathematical operators to model formulations that are further evolved, eventually identifying the most suitable structures. In contrast to most other machine learning regression techniques, the GEP approach generates models that allow for prediction and possibly for interpretation. Our study is based on two cases: artificially generated data and real observations. Simulations based on artificial data show that GEP is successful in identifying prescribed functions with the prediction capacity of the models comparable to four state-of-the-art machine learning methods (Random Forests, Support Vector Machines, Artificial Neural Networks, and Kernel Ridge Regressions). The case of real observations explores different components of terrestrial respiration at an oak forest in south-east England. We find that GEP retrieved models are often better in prediction than established respiration models. Furthermore, the structure of the GEP models offers new insights to driver selection and interactions. We find previously unconsidered exponential dependencies of respiration on seasonal ecosystem carbon assimilation and water dynamics. However, we also noticed that the GEP models are only partly portable across respiration components; equifinality issues possibly preventing the identification of a "general" terrestrial respiration model. Overall, GEP is a promising tool to uncover new model structures for terrestrial ecology in the data rich era, complementing the traditional approach of model building.

scholarly journals Deep learning shows declining groundwater levels in Germany until 2100 due to climate change

2021 ◽  
Author(s):  
Andreas Wunsch ◽  
Tanja Liesch ◽  
Stefan Broda
Keyword(s):  
Climate Change ◽  
Machine Learning ◽  
Neural Networks ◽  
Groundwater Level ◽  
Groundwater Resources ◽  
Anthropogenic Factors ◽  
Climate Projections ◽  
Climate Signal ◽  
Groundwater Levels ◽  
Groundwater Level Prediction

Abstract In this study we investigate how climate change will directly influence the groundwater resources in Germany during the 21st century. We apply a machine learning groundwater level prediction framework, based on convolutional neural networks to 118 sites well distributed over Germany to assess the groundwater level development under the RCP8.5 scenario, based on six selected climate projections, which represent 80% of the bandwidth of the possible future climate signal for Germany. We consider only direct meteorological inputs, while highly uncertain anthropogenic factors such as groundwater extractions are excluded. We detected significant declining trends of groundwater levels for most of the sites, revealing a spatial pattern of stronger decreases especially in the northern and eastern part of Germany, emphasizing already existing decreasing trends in these regions. We can further show an increased variability and longer periods of low groundwater levels during the annual cycle towards the end of the century.

scholarly journals Aerosol optical depth prediction using machine learning techniques

2021 ◽  
Author(s):  
Stavros Andreas Logothetis ◽  
Vasileios Salamalikis ◽  
Andreas Kazantzidis
Keyword(s):  
Machine Learning ◽  
Aerosol Optical Depth ◽  
Optical Depth ◽  
Multivariate Adaptive Regression Splines ◽  
Surface Radiation ◽  
Machine Learning Techniques ◽  
Gradient Boosting ◽  
Support Vector ◽  
Climate Projections ◽  
Extreme Gradient Boosting

<p>Aerosol optical depth (AOD) describes adequately aerosols’s burden and extinction within an atmospheric column. AOD can be retrieved using remote sensing instruments such as ground-based sun photometers. Despite the very good quality of ground based AOD measurements, their spatiotemporal coverage is restricted. In this study, an alternative approach of AOD estimation is proposed with the synergy of ground-based measurements and machine learning (ML) techniques, in order to expand and complement the existing spatiotemporal capabilities of AOD data. The ML algorithms which are implemented are: Random Forests, Gradient Boosting Machines, Extreme Gradient Boosting Machines, Support Vector Regression, K-nearest Neighbors Regression, and Multivariate Adaptive Regression Splines. Each model receives as input information the Global Horizontal Irradiance (GHI) as well as water vapor (WV) content in hourly basis and under clear skies. A randomized cross-validation search scheme is implemented to obtain the optimal hyperparameters and avoid overfitting for each ML algorithm. GHI and WV are retrieved from Baseline Surface Radiation Network (BSRN) and NASA’s Modern-Era Retrospective Analysis for Research and Applications-2 (MERRA-2) reanalysis product respectively. AOD estimations are evaluated against AOD from AErosol RObotic NETwork (AERONET) inversion product, using the Level 2.0 Version 3 (L2V3) which provides cloud-screened and quality assured measurements. In total, 29 collocated AERONET-BSRN stations are used spanning from 2000 to 2019. Since, the aerosol pattern is different at each site, the effect of various aerosol types is further investigated. ML-based AOD predictions are adequately good, highlighting the feasibility of ML algorithms on producing AOD data. The results of this study could be useful for direct normal irradiance estimations as well as aerosols radiative effect calculations and climate projections.</p>

MODELING PRESENT AND PROSPECTIVE DISTRIBUTION OF PHYTEUMA GENUS IN CARPATHIAN REGION WITH MACHINE LEARNING TECHNIQUES USING OPEN CLIMATIC AND SOIL DATA

2021 ◽  
Author(s):  
Alexander Mkrtchian
Keyword(s):  
Machine Learning ◽  
Open Data ◽  
Boosted Regression Trees ◽  
Machine Learning Techniques ◽  
Climate Projections ◽  
Climatic Data ◽  
Carpathian Region ◽  
Distribution Modeling ◽  
Learning Techniques ◽  
Plant Taxon

"Species distribution modeling can be effectively carried out using open data and data analysis tools with machine learning techniques. Modeling of the distribution of Phyteuma genus in the Carpathian region has been carried out with data from the GBIF database, climatic data from the Worldclim database, and soil properties data from Soilgrids soil information system. Spatial distribution modeling was accomplished with machine learning techniques that have marked advantages over more traditional statistical methods, like the ability to fit complex nonlinear relationships common in ecology. Four methods have been examined: Maxent, Random Forest, Artificial Neural Networks (ANN), and Boosted Regression Trees. AUC and TSS criteria calculated for testing data with cross-validation have been applied for assessing the performance of the models and to tune their parameters. ANN with a reduced set of predictor variables (6 from initial 21) appeared to fare the best and was applied for predictive modeling. Prospective data based on future climate projections from Worldclim were input to the model to get the prospective distribution of the plant taxon considering expected climate changes under different RCPs"

Mind wandering as data augmentation: How mental travel supports abstraction

2020 ◽  
Vol 43 ◽  
Author(s):  
Myrthe Faber
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Mental Content ◽  
Mind Wandering ◽  
Theoretical Framework ◽  
Important Addition

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.

Sign in / Sign up

Export Citation Format

Share Document