scholarly journals Evaluating Traditional Empirical Models and BPNN Models in Monitoring the Concentrations of Chlorophyll-A and Total Suspended Particulate of Eutrophic and Turbid Waters

Water ◽  
2021 ◽  
Vol 13 (5) ◽  
pp. 650 ◽  
Author(s):  
Bo Jiang ◽  
Hailong Liu ◽  
Qianguo Xing ◽  
Jiannan Cai ◽  
Xiangyang Zheng ◽  
...  
Keyword(s):  
Machine Learning ◽  
Water Samples ◽  
Empirical Models ◽  
Total Suspended Particulate ◽  
Learning Models ◽  
Band Ratio ◽  
Chl A ◽  
Turbid Waters ◽  
Suspended Particulate ◽  
Machine Learning Models

In order to use in situ sensed reflectance to monitor the concentrations of chlorophyll-a (Chl-a) and total suspended particulate (TSP) of waters in the Pearl River Delta, which is featured by the highly developed network of rivers, channels and ponds, 135 sets of simultaneously collected water samples and reflectance were used to test the performance of the traditional empirical models (band ratio, three bands) and the machine learning models of a back-propagation neural network (BPNN). The results of the laboratory analysis with the water samples show that the Chl-a ranges from 3 to 256 µg·L−1 with an average of 39 µg·L−1 while the TSP ranges from 8 to 162 mg·L−1 and averages 42.5 mg·L−1. Ninety sets of 135 samples are used as training data to develop the retrieval models, and the remaining ones are used to validate the models. The results show that the proposed band ratio models, the three-band combination models, and the corresponding BPNN models are generally successful in estimating the Chl-a and the TSP, and the mean relative error (MRE) can be lower than 30% and 25%, respectively. However, the BPNN models have no better performance than the traditional empirical models, e.g., in the estimation of TSP on the basis of the reflectance at 555 and 750 nm (R555 and R750, respectively), the model of BPNN (R555, R750) has an MRE of 23.91%, larger than that of the R750/R555 model. These results suggest that these traditional empirical models are usable in monitoring the optically active water quality parameters of Chl-a and TSP for eutrophic and turbid waters, while the machine learning models have no significant advantages, especially when the cost of training samples is considered. To improve the performance of machine learning models in future applications on the basis of ground sensor networks, large datasets covering various water situations and optimization of input variables of band configuration should be strengthened.

scholarly journals Correction of Light Scattering-Based Total Suspended Particulate Measurements through Machine Learning

Atmosphere ◽  
2020 ◽  
Vol 11 (2) ◽  
pp. 139 ◽  
Author(s):  
Qiaofeng Guo ◽  
Zhu Zhu ◽  
Zhen Cheng ◽  
Shuhong Xu ◽  
Xiaoliang Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Light Scattering ◽  
Support Vector ◽  
Total Suspended Particulate ◽  
Hygroscopic Growth ◽  
Learning Models ◽  
Suspended Particulate ◽  
Scattering Measurements ◽  
Machine Learning Models ◽  
Mass Concentrations

Instruments based on light scattering used to measure total suspended particulate (TSP) concentrations have the advantages of fast response, small size, and low cost compared to the gravimetric reference method. However, the relationship between scattering intensity and TSP mass concentration varies nonlinearly with both environmental conditions and particle properties, making it difficult to make corrections. This study applied four machine learning models (support vector machines, random forest, gradient boosting regression trees, and an artificial neural network) to correct scattering measurements for TSP mass concentrations. A total of 1141 hourly records of collocated gravimetric and light scattering measurements taken at 17 urban sites in Shanghai, China were used for model training and validation. All four machine learning models improved the linear regressions between scattering and gravimetric mass by increasing slopes from 0.4 to 0.9–1.1 and coefficients of determination from 0.1 to 0.8–0.9. Partial dependence plots indicate that TSP concentrations determined by light scattering instruments increased continuously in the PM2.5 concentration range of ~0–80 µg/m3; however, they leveled off above PM10 and TSP concentrations of ~60 and 200 µg/m3, respectively. The TSP mass concentrations determined by scattering showed an exponential growth after relative humidity exceeded 70%, in agreement with previous studies on the hygroscopic growth of fine particles. This study demonstrates that machine learning models can effectively improve the correlation between light scattering measurements and TSP mass concentrations with filter-based methods. Interpretation analysis further provides scientific insights into the major factors (e.g., hygroscopic growth) that cause scattering measurements to deviate from TSP mass concentrations besides other factors like fluctuation of mass density and refractive index.

scholarly journals Global solar radiation modeling using different machine learning and empirical models in Northeast China

2021 ◽  
Author(s):  
Yue Jia ◽  
Yongjun Su ◽  
Fengchun Wang ◽  
Pengcheng Li ◽  
Shuyi Huo
Keyword(s):  
Machine Learning ◽  
Solar Radiation ◽  
Solar Energy ◽  
Northeast China ◽  
Sunshine Duration ◽  
Meteorological Data ◽  
Global Solar Radiation ◽  
Empirical Models ◽  
Learning Models ◽  
Machine Learning Models

Abstract Reliable global solar radiation (Rs) information is crucial for the design and management of solar energy systems for agricultural and industrial production. However, Rs measurements are unavailable in many regions of the world, which impedes the development and application of solar energy. To accurately estimate Rs, this study developed a novel machine learning model, called a Gaussian exponential model (GEM), for daily global Rs estimation. The GEM was compared with four other machine learning models and two empirical models to assess its applicability using daily meteorological data from 1997–2016 from four stations in Northeast China. The results showed that the GEM with complete inputs had the best performance. Machine learning models provided better estimates than empirical models when trained by the same input data. Sunshine duration was the most effective factor determining the accuracy of the machine learning models. Overall, the GEM with complete inputs had the highest accuracy and is recommended for modeling daily Rs in Northeast China.

Development of an Optimal Model For Rate of Penetration Rop Using Deep Neural Networks DNN.

2021 ◽  
Author(s):  
_ _
Keyword(s):  
Machine Learning ◽  
Empirical Model ◽  
Empirical Models ◽  
The Other ◽  
Gradient Boosting ◽  
Past Century ◽  
Learning Models ◽  
Continuous Increase ◽  
Unseen Data ◽  
Machine Learning Models

Abstract For the past century, optimization of drilling has caught the eyes of many researchers. The main areas center on ROP, fluid treatment, and bit selection. They all share the same goal of maximizing ROP and reducing NPT. In other to develop an optimal control system, ROP must be predicted accurately, unfortunately, it is a complex parameter that is affected by multiple drilling parameters, rock properties, fluid properties, and bit selection. Models used for prediction have developed from empirical models like Bourgoyne and Young's to more intelligent models such as SVM and ANN. With the continuous increase in data obtained from sensors while drilling, there is still much work to be done in this field. In this research, the improvement of an empirical model and the development of an intelligent model are presented. The Bourgoyne and Young's model uses multiple linear regression to estimate coefficients which it then inserts into an empirical formula to predict ROP. This model was modified using non-linear curve-fitting to estimate the coefficients and make it reduce bias to generalize better. Machine learning models such as Gradient Boosting, Random Forest, ANN, and DNN were used in the development of a predictive model for the ROP. These models were easier to develop compared to the empirical model since they rely more on data rather than statistical formulas. The data used in this research include drilling data from 3 wells drilled in 2 fields within the Niger Delta region in Nigeria. The models were developed and trained on one of the wells, while the remaining two were used for testing the performance of the models. The modified empirical model improved the efficiency of the base model by 14% during validation but performs poorly on unseen data from the other two wells. The Machine learning models outperform the empirical models and perform accurately on unseen data from the other wells. DNN was the best performing model achieving an average accuracy of 0.987 for the 3 wells.

Improving XGBoost with Imagination Sampling

2020 ◽  
Vol 2 (1) ◽  
pp. 3-6
Author(s):  
Eric Holloway
Keyword(s):  
Machine Learning ◽  
General System ◽  
Learning Models ◽  
Starting Point ◽  
Machine Learning Models

Imagination Sampling is the usage of a person as an oracle for generating or improving machine learning models. Previous work demonstrated a general system for using Imagination Sampling for obtaining multibox models. Here, the possibility of importing such models as the starting point for further automatic enhancement is explored.

Epigenetic Target Prediction with Accurate Machine Learning Models

2021 ◽  
Author(s):  
Norberto Sánchez-Cruz ◽  
Jose L. Medina-Franco
Keyword(s):  
Machine Learning ◽  
Small Molecules ◽  
Predictive Models ◽  
Large Scale ◽  
Target Prediction ◽  
Quantitative Measure ◽  
Learning Models ◽  
Discovery Research ◽  
Drug Discovery Research ◽  
Machine Learning Models

<p>Epigenetic targets are a significant focus for drug discovery research, as demonstrated by the eight approved epigenetic drugs for treatment of cancer and the increasing availability of chemogenomic data related to epigenetics. This data represents a large amount of structure-activity relationships that has not been exploited thus far for the development of predictive models to support medicinal chemistry efforts. Herein, we report the first large-scale study of 26318 compounds with a quantitative measure of biological activity for 55 protein targets with epigenetic activity. Through a systematic comparison of machine learning models trained on molecular fingerprints of different design, we built predictive models with high accuracy for the epigenetic target profiling of small molecules. The models were thoroughly validated showing mean precisions up to 0.952 for the epigenetic target prediction task. Our results indicate that the herein reported models have considerable potential to identify small molecules with epigenetic activity. Therefore, our results were implemented as freely accessible and easy-to-use web application.</p>

Sign in / Sign up

Export Citation Format

Share Document