Mapping pasture biomass in Mongolia using Partial Least Squares, Random Forest regression and Landsat 8 imagery

2018 ◽  
Vol 40 (8) ◽  
pp. 3204-3226 ◽  
Author(s):  
Munkhdulam Otgonbayar ◽  
Clement Atzberger ◽  
Jonathan Chambers ◽  
Amarsaikhan Damdinsuren
Keyword(s):  
Random Forest ◽  
Least Squares ◽  
Partial Least Squares ◽  
Landsat 8 ◽  
Random Forest Regression

scholarly journals Research on data correction method of micro air quality detector based on combination of partial least squares and random forest regression

2021 ◽  
Author(s):  
Bing Liu ◽  
Wangwang Yu ◽  
Yishu Wang ◽  
Qibao Lv ◽  
Chaoyang Li
Keyword(s):  
Air Quality ◽  
Random Forest ◽  
Least Squares ◽  
Partial Least Squares ◽  
Partial Least Squares Regression ◽  
Partial Least Square ◽  
Monitoring Station ◽  
Least Squares Regression ◽  
Random Forest Regression ◽  
National Monitoring

Abstract The issue of air quality has attracted more and more attention. The main methods for monitoring the concentration of pollutants in the air include national monitoring station monitoring and micro air quality detector testing. Since the electrochemical sensor of the micro air quality detector is susceptible to interference, the monitored data has a certain deviation. In this paper, the combined model of partial least square regression and random forest regression (PLS-RFR) is used to correct the detection data of the micro air quality detector. First, correlation analysis is used to find out the factors that affect the concentration of pollutants. Second, partial least squares regression is used to give the quantitative relationship of the influence of each influencing factor on the concentration of pollutants. Finally, the predicted value of partial least squares regression and various influencing factors are used as independent variables, and the pollutant concentration monitored by the national monitoring station is used as the dependent variable, and the PLS-RFR model is obtained with the help of random forest software package. Relative Mean Absolute Percent Error (MAPE), Mean Absolute Error (MAE), goodness of fit (R2), and Root Mean Square Error (RMSE) are used as evaluation indicators to compare PLS-RFR model, support vector machine model and multilayer perceptron neural network. The results show that no matter which evaluation index, the prediction effect of the PLS-RFR model is the best, and the model has a good prediction effect in the training set or the test set, indicating that the model has good generalization ability. This model can play an active role in the promotion and deployment of micro air quality detectors.

scholarly journals A Pattern Recognition Diagnostic Model to Restore and Emulate Knee Mobility

2021 ◽  
Author(s):  
Bayu Sukmanto ◽  
Sadaira Packer ◽  
Muhammad Gulfam ◽  
David Hollinger
Keyword(s):  
Pattern Recognition ◽  
Random Forest ◽  
Decision Tree ◽  
Least Squares ◽  
Real Time ◽  
Partial Least Squares ◽  
Partial Least Squares Regression ◽  
Secondary Outcome ◽  
Least Squares Regression ◽  
Tree Classifier

Electromyography (EMG) is an electrical voltage potential linked to muscle contraction, resulting in human joint motion, such as knee flexion. Knee injuries, such as knee osteoarthritis (KOA), disrupt functional mobility of the knee joint and subsequently atrophy the muscles controlling knee movement during activities of daily living (ADL). Consequently, weakened muscles exhibiting deteriorated EMG signal fidelity are hypothesized to have discernible signal patterns from a healthy individual's EMG signals. Pattern recognition algorithms are useful for mapping a set of complex inputs (EMG signals and knee angles) to classify knee health status (injured vs. healthy). A secondary outcome is to predict future knee angles from previous input signals to inform a robotic knee exoskeleton to apply real-time torque assistance to a patient during ADL. A Decision Tree Classifier, Random Forest, Naive Bayes, and a Feed-Forward Neural Network (Fully Connected) were used for binary classification (healthy vs. injured). Partial Least Squares Regression, Decision Tree Regressor, and XGBoost were used to predict future joint angles for the regression task (knee angle prediction). Overall, the Random Forest Classifier had the best overall classification performance. XGBoost and Decision Tree Regression performed the best among regression algorithms for predicting real-time angles during walking while Partial Least Squares Regression performed the best during the standing tasks. In summary, our Machine Learning methods are useful for assisting clinicians and patients during physical rehabilitation by providing quantitative insight into the patient's neuromuscular control of the knee.

scholarly journals Prediction of Grape Sap Flow in a Greenhouse Based on Random Forest and Partial Least Squares Models

Water ◽  
2021 ◽  
Vol 13 (21) ◽  
pp. 3078
Author(s):  
Xuelian Peng ◽  
Xiaotao Hu ◽  
Dianyu Chen ◽  
Zhenjiang Zhou ◽  
Yinyin Guo ◽  
...  
Keyword(s):  
Random Forest ◽  
Least Squares ◽  
Partial Least Squares ◽  
Flow Rate ◽  
Sap Flow ◽  
Deficit Irrigation ◽  
Coefficient Of Determination ◽  
Growth Stages ◽  
Irrigation Amount ◽  
Flow Rates

Understanding variations in sap flow rates and the environmental factors that influence sap flow is important for exploring grape water consumption patterns and developing reasonable greenhouse irrigation schedules. Three irrigation levels were established in this study: adequate irrigation (W1), moderate deficit irrigation (W2) and deficit irrigation (W3). Grape sap flow estimation models were constructed using partial least squares (PLS) and random forest (RF) algorithms, and the simulation accuracy and stability of these models were evaluated. The results showed that the daily mean sap flow rates in the W2 and W3 treatments were 14.65 and 46.94% lower, respectively, than those in the W1 treatment, indicating that the average daily sap flow rate increased gradually with an increase in the irrigation amount within a certain range. Based on model error and uncertainty analyses, the RF model had better simulation results in the different grape growth stages than the PLS model did. The coefficient of determination and Willmott’s index of agreement for RF model exceeded 0.78 and 0.90, respectively, and this model had smaller root mean square error and d-factor (evaluation index of model uncertainty) values than the PLS model did, indicating that the RF model had higher prediction accuracy and was more stable. The relative importance of the model predictors was determined. Moreover, the RF model more comprehensively reflected the influence of meteorological factors and the moisture content in different soil layers on the sap flow rate than the PLS model did. In summary, the RF model accurately simulated sap flow rates, which is important for greenhouse grape irrigation.

scholarly journals Extension of pQSAR: Ensemble Model Generated by Random Forest and Partial Least Squares Regressions

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 180087-180099
Author(s):  
Byung Chun Kim ◽  
Dosang Joe ◽  
Youngho Woo ◽  
Yongkuk Kim ◽  
Gangjoon Yoon
Keyword(s):  
Random Forest ◽  
Least Squares ◽  
Partial Least Squares ◽  
Ensemble Model

scholarly journals SYNERGETIC USE OF OPTICAL, MICROWAVE AND THERMAL SATELLITE DATA FOR NON-PARAMETRIC ESTIMATION OF WHEAT GRAIN YIELD

2019 ◽  
Vol XLII-3/W6 ◽  
pp. 195-199
Author(s):  
K. K. Choudhary ◽  
V. Pandey ◽  
C. S. Murthy ◽  
M. K. Poddar
Keyword(s):  
Time Series ◽  
Random Forest ◽  
Grain Yield ◽  
Crop Yield ◽  
Satellite Data ◽  
Parametric Estimation ◽  
Landsat 8 ◽  
Wheat Grain ◽  
Random Forest Regression ◽  
Multi Temporal

<p><strong>Abstract.</strong> Crop yield maps are very crucial inputs for different practical applications like crop production estimation, pay-out of crop insurance, yield gap analysis etc. Satellite derived vegetation indices across different electromagnetic region has the ability to explain the variation in crop yield and can be used for prediction of yield before harvesting. This study utilised indices derived from multi-temporal Optical, Thermal and Radar data for developing model for Wheat (Triticum aestivum) grain yield using Machine learning approaches i.e., Random Forest Regression (RFR). Time series of Sentinel-2 derived Normalized difference vegetation index (NDVI), Normalized difference water Index (NDWI), Landsat-8 derived GPP using LST-EVI relationship (Temparature-Greeness model) and Sentinel-1 derived cross-polarization backscatter ratio (&amp;sigma;VH/&amp;sigma;VV) were used as predictor for wheat yield estimation. Actual grain yield measurements at ground were carried out at the end of the season over 178 locations. Seventy five percent of ground yield data were used for training of the model and rest twenty five percent data were used for its validation. All the datasets were grouped into ten fortnightly datasets ranging from November 2017 to March 2018. Through the random forest regression using time-series of NDVI alone, wheat grain yields were estimated with an RMSE of 9.8&amp;thinsp;Q&amp;thinsp;ha<sup>&amp;minus;1</sup>. Subsequently by adding the multi-temporal NDWI, GPP and σVH/σVV led to the improvement of RMSE to 8.7, 7.6 and 7.4&amp;thinsp;Q&amp;thinsp;ha<sup>&amp;minus;1</sup> respectively. Variable importance based on the out of box error showed the significance of NDVI, NDWI and GPP during Dec-Jan and &amp;sigma;VH/&amp;sigma;VV during Feb for wheat grain estimation. It was concluded that the RFR algorithm together with the indices from optical, thermal and microwave satellite data can able to produced significantly accurate estimates of wheat grain yield.</p>

Sign in / Sign up

Export Citation Format

Share Document