MODIS-Based Estimation of Terrestrial Latent Heat Flux over North America Using Three Machine Learning Algorithms

Abstract Long-term changes in land–atmosphere interactions during spring and summer are examined over North America. A suite of models from phase 5 of the Coupled Model Intercomparison Project simulating preindustrial, historical, and severe future climate change scenarios are examined for changes in soil moisture, surface fluxes, atmospheric boundary layer characteristics, and metrics of land–atmosphere coupling. Simulations of changes from preindustrial to modern conditions show warming brings stronger surface fluxes at high latitudes, while subtropical regions of North America respond with drier conditions. There is a clear anthropogenic aerosol response in midlatitudes that reduces surface radiation and heat fluxes, leading to shallower boundary layers and lower cloud base. Over the Great Plains, the signal does not reflect a purely radiatively forced response, showing evidence that the expansion of agriculture may have offset the aerosol impacts on the surface energy and water cycle. Future changes show soils are projected to dry across North America, even though precipitation increases north of a line that retreats poleward from spring to summer. Latent heat flux also has a north–south dipole of change, increasing north and decreasing south of a line that also moves northward with the changing season. Metrics of land–atmosphere feedback increase over most of the continent but are strongest where latent heat flux increases in the same location and season where precipitation decreases. Combined with broadly elevated cloud bases and deeper boundary layers, land–atmosphere interactions are projected to become more important in the future with possible consequences for seasonal climate prediction.

Download Full-text

Impact of the Anomalous Latent Heat Flux Over the Kuroshio Extension on Western North American Rainfall in Spring: Interannual Variation and Mechanism

Frontiers in Earth Science ◽

10.3389/feart.2020.609619 ◽

2021 ◽

Vol 8 ◽

Author(s):

Jingchao Long ◽

Chunlei Liu ◽

Zifeng Liu ◽

Jianjun Xu

Keyword(s):

Heat Flux ◽

North America ◽

Latent Heat ◽

Latent Heat Flux ◽

Cyclonic Circulation ◽

Western Canada ◽

Jet Stream ◽

The Impact ◽

The Kuroshio ◽

Anomalous Cyclonic Circulation

The Kuroshio and its extension (KE) significantly influences regional climate through meridional heat transport from the tropical ocean. In this study, the observational and reanalysis datasets are used to investigate the impact of the latent heat flux (LHF) over the KE region on downstream rainfall and the underlying mechanism. The result shows a “seesaw” structure in rainfall anomaly, dominating the Western Canada and the southwestern North America with a correlation coefficient of 0.77 between the two modes. In strong LHF years, strengthened LHF favors to enhance precipitation in the Western Canada and reduce that in the southwestern North America. This is primarily associated with an anomalous cyclonic circulation over the KE region, which enhances southwesterly precipitation and latent heating in the middle troposphere. The heating excites an anomalous cyclonic circulation to its west and an anticyclonic circulation to its east, helping to reinforce the existing anomalous cyclonic circulation in turn and form a positive feedback. The conditions associated with La Niña events favor to above processes. To the upper troposphere, the deepened anomalous cyclonic circulation due to enhanced eddy activities and atmospheric baroclinic instability over the KE strengthens subtropical westerly jet stream and thereby extends eastward on the 200 hPa level. Correspondingly, an elongated zonally lower level cyclonic circulation anomaly across the North Pacific leads to a moisture convergence in the Western Canada, which is mainly resulted from the anomalous positive vorticity advection over the left side of the exit region of the jet stream. The opposite circumstance occurs in weak LHF years, presenting an opposed anomalous circulation and rainfall pattern.

Download Full-text

Gap-Filling Eddy Covariance Latent Heat Flux: Inter-Comparison of Four Machine Learning Model Predictions and Uncertainties in Forest Ecosystem

Remote Sensing ◽

10.3390/rs13244976 ◽

2021 ◽

Vol 13 (24) ◽

pp. 4976

Author(s):

Muhammad Sarfraz Khan ◽

Seung Bae Jeon ◽

Myeong-Hun Jeong

Keyword(s):

Machine Learning ◽

Heat Flux ◽

Eddy Covariance ◽

Latent Heat ◽

Latent Heat Flux ◽

Model Performance ◽

Support Vector ◽

Two Dimensional ◽

Gap Filling

Environmental monitoring using satellite remote sensing is challenging because of data gaps in eddy-covariance (EC)-based in situ flux tower observations. In this study, we obtain the latent heat flux (LE) from an EC station and perform gap filling using two deep learning methods (two-dimensional convolutional neural network (CNN) and long short-term memory (LSTM) neural networks) and two machine learning (ML) models (support vector machine (SVM), and random forest (RF)), and we investigate their accuracies and uncertainties. The average model performance based on ~25 input and hysteresis combinations show that the mean absolute error is in an acceptable range (34.9 to 38.5 Wm−2), which indicates a marginal difference among the performances of the four models. In fact, the model performance is ranked in the following order: SVM > CNN > RF > LSTM. We conduct a robust analysis of variance and post-hoc tests, which yielded statistically insignificant results (p-value ranging from 0.28 to 0.76). This indicates that the distribution of means is equal within groups and among pairs, thereby implying similar performances among the four models. The time-series analysis and Taylor diagram indicate that the improved two-dimensional CNN captures the temporal trend of LE the best, i.e., with a Pearson’s correlation of > 0.87 and a normalized standard deviation of ~0.86, which are similar to those of in situ datasets, thereby demonstrating its superiority over other models. The factor elimination analysis reveals that the CNN performs better when specific meteorological factors are removed from the training stage. Additionally, a strong coupling between the hysteresis time factor and the accuracy of the ML models is observed.

Download Full-text

Supplemental Material for One Model to Rule Them All? Using Machine Learning Algorithms to Determine the Number of Factors in Exploratory Factor Analysis

Psychological Methods ◽

10.1037/met0000262.supp ◽

2020 ◽

Keyword(s):

Machine Learning ◽

Factor Analysis ◽

Exploratory Factor Analysis ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Number Of Factors

Download Full-text

Forecasting US movies box office performances in Turkey using machine learning algorithms

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189120 ◽

2020 ◽

Vol 39 (5) ◽

pp. 6579-6590

Author(s):

Sandy Çağlıyor ◽

Başar Öztayşi ◽

Selime Sezgin

Keyword(s):

Machine Learning ◽

Global Economy ◽

Learning Algorithms ◽

Forecast Model ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

High Stakes ◽

Box Office ◽

Industry Forecast ◽

The Impact

The motion picture industry is one of the largest industries worldwide and has significant importance in the global economy. Considering the high stakes and high risks in the industry, forecast models and decision support systems are gaining importance. Several attempts have been made to estimate the theatrical performance of a movie before or at the early stages of its release. Nevertheless, these models are mostly used for predicting domestic performances and the industry still struggles to predict box office performances in overseas markets. In this study, the aim is to design a forecast model using different machine learning algorithms to estimate the theatrical success of US movies in Turkey. From various sources, a dataset of 1559 movies is constructed. Firstly, independent variables are grouped as pre-release, distributor type, and international distribution based on their characteristic. The number of attendances is discretized into three classes. Four popular machine learning algorithms, artificial neural networks, decision tree regression and gradient boosting tree and random forest are employed, and the impact of each group is observed by compared by the performance models. Then the number of target classes is increased into five and eight and results are compared with the previously developed models in the literature.

Download Full-text

Intelligent system of English composition scoring model based on improved machine learning algorithm

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189235 ◽

2020 ◽

pp. 1-11

Author(s):

Jie Liu ◽

Lin Lin ◽

Xiufang Liang

Keyword(s):

Machine Learning ◽

Evaluation System ◽

Intelligent System ◽

Learning Algorithm ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Assessment System ◽

English Composition ◽

Region Extraction ◽

Constraint Model

The online English teaching system has certain requirements for the intelligent scoring system, and the most difficult stage of intelligent scoring in the English test is to score the English composition through the intelligent model. In order to improve the intelligence of English composition scoring, based on machine learning algorithms, this study combines intelligent image recognition technology to improve machine learning algorithms, and proposes an improved MSER-based character candidate region extraction algorithm and a convolutional neural network-based pseudo-character region filtering algorithm. In addition, in order to verify whether the algorithm model proposed in this paper meets the requirements of the group text, that is, to verify the feasibility of the algorithm, the performance of the model proposed in this study is analyzed through design experiments. Moreover, the basic conditions for composition scoring are input into the model as a constraint model. The research results show that the algorithm proposed in this paper has a certain practical effect, and it can be applied to the English assessment system and the online assessment system of the homework evaluation system algorithm system.

Download Full-text

The Unlearnable Checkerboard Pattern

Communications of the Blyth Institute ◽

10.33014/issn.2640-5652.1.2.holloway.1 ◽

2019 ◽

Vol 1 (2) ◽

pp. 78-80

Author(s):

Eric Holloway

Keyword(s):

Machine Learning ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Checkerboard Pattern ◽

Simple Task

Detecting some patterns is a simple task for humans, but nearly impossible for current machine learning algorithms. Here, the "checkerboard" pattern is examined, where human prediction nears 100% and machine prediction drops significantly below 50%.

Download Full-text