Fuel properties of hydrochar and pyrochar: Prediction and exploration with machine learning

Li, Jie; Pan, Lanjia; Suvarna, Manu; Tong, Yen Wah; Wang, Xiaonan

doi:10.1016/j.apenergy.2020.115166

Cited by 157 publications

(60 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM is a ML algorithm that uses the nonlinear kernel function to map the initial training samples to the high-dimensional feature space, thus transforming the problem from nonlinear to linear and obtaining the optimal solution [9]. All of the input data were normalized according to the studies of Li et al [15,16]. The ratio of the training dataset to the test dataset was 8:2, and cross validation was carried out to avoid bias in the training process.…”

Section: Model Constructionmentioning

confidence: 99%

See 1 more Smart Citation

The Estimation of the Higher Heating Value of Biochar by Data-Driven Modeling

Chen¹,

Ding²,

Wang³

et al. 2022

Journal of Renewable Materials

Self Cite

View full text Add to dashboard Cite

Biomass is a carbon-neutral renewable energy resource. Biochar produced from biomass pyrolysis exhibits preferable characteristics and potential for fossil fuel substitution. For time-and cost-saving, it is vital to establish predictive models to predict biochar properties. However, limited studies focused on the accurate prediction of HHV of biochar by using proximate and ultimate analysis results of various biochar. Therefore, the multi-linear regression (MLR) and the machine learning (ML) models were developed to predict the measured HHV of biochar from the experiment data of this study. In detail, 52 types of biochars were produced by pyrolysis from rice straw, pig manure, soybean straw, wood sawdust, sewage sludge, Chlorella Vulgaris, and their mixtures at the temperature ranging from 300 to 800°C. The results showed that the co-pyrolysis of the mixed biomass provided an alternative method to increase the yield of biochar production. The contents of ash, fixed carbon (FC), and C increased as the incremental pyrolysis temperature for most biochars. The Pearson correlation (r) and relative importance analysis between HHV values and the indicators derived from the proximate and ultimate analysis were carried out, and the measured HHV was used to train and test the MLR and the ML models. Besides, ML algorithms, including gradient boosted regression, random forest, and support vector machine, were also employed to develop more widely applicable models for predicting HHV of biochar from an expanded dataset (total 149 data points, including 97 data collected from the published literature). Results showed HHV had strong correlations (|r| > 0.9, p < 0.05) with ash, FC, and C. The MLR correlations based on either proximate or ultimate analysis showed acceptable prediction performance with test R 2 > 0.90. The ML models showed better performance with test R 2 around 0.95 (random forest) and 0.97-0.98 before and after adding extra data for model construction, respectively. Feature importance analysis of the ML models showed that ash and C were the most important inputs to predict biochar HHV.

show abstract

Section: Model Constructionmentioning

confidence: 99%

“…And R 2 can be used to determine the degree of goodness of the proposed correlations. The higher the R 2 and lower the RMSE and MAE meant the better the model accuracy [15,17].…”

Section: Model Constructionmentioning

confidence: 99%

The Estimation of the Higher Heating Value of Biochar by Data-Driven Modeling

Chen¹,

Ding²,

Wang³

et al. 2022

Journal of Renewable Materials

Self Cite

View full text Add to dashboard Cite

show abstract

“…PFI is a new global model-agnostic explanation technique that was recently used to identify the most relevant features in many fields, such as medicine [45], agriculture [46], and engineering [47]. Similarly, the SHAP method has been applied successfully to interpret local and global ML predictions in several studies in order to predict the risk of water erosion [48], estimate pairwise acquisition [49], investigate the factors that contribute to freight truck-related crashes [50], estimate the occurrence of benthic macroinvertebrate species [51], and predict the fuel properties of the chars [52].…”

Section: Locationmentioning

confidence: 99%

An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction

et al. 2021

View full text Add to dashboard Cite

Machine learning (ML) models are commonly used in solar modeling due to their high predictive accuracy. However, the predictions of these models are difficult to explain and trust. This paper aims to demonstrate the utility of two interpretation techniques to explain and improve the predictions of ML models. We compared first the predictive performance of Light Gradient Boosting (LightGBM) with three benchmark models, including multilayer perceptron (MLP), multiple linear regression (MLR), and support-vector regression (SVR), for estimating the global solar radiation (H) in the city of Fez, Morocco. Then, the predictions of the most accurate model were explained by two model-agnostic explanation techniques: permutation feature importance (PFI) and Shapley additive explanations (SHAP). The results indicated that LightGBM (R2 = 0.9377, RMSE = 0.4827 kWh/m2, MAE = 0.3614 kWh/m2) provides similar predictive accuracy as SVR, and outperformed MLP and MLR in the testing stage. Both PFI and SHAP methods showed that extraterrestrial solar radiation (H0) and sunshine duration fraction (SF) are the two most important parameters that affect H estimation. Moreover, the SHAP method established how each feature influences the LightGBM estimations. The predictive accuracy of the LightGBM model was further improved slightly after re-examination of features, where the model combining H0, SF, and RH was better than the model with all features.

show abstract

“…In the context of environmental impact, the authors tried to estimate: the illegal disposal of waste (Yang, Fan, et al, 2019), the emissions of polluting gases from the inadequate final disposal of waste (Dimishkovsk et al, 2019;Kumar et al, 2016;Vu et al, 2018), soil pollution by heavy metals (Perez-Alonso et al, 2017) and the calorific value of waste as a potential source of energy (Baghban and Shamshirband, 2019;Bagheri et al, 2019;Boumanchar et al, 2019;Drudi et al, 2019;Li et al, 2020;Rostami and Baghban, 2018). In terms of economic impact, studies sought to predict the generation of waste to promote cost efficiency in the provision of services and to identify the best form of service provision (Pérez-López et al, 2016).…”

Section: Main Challenges and Opportunitiesmentioning

confidence: 99%

Data mining and knowledge discovery in databases for urban solid waste management: A scientific literature review

et al. 2021

View full text Add to dashboard Cite

The processes related to solid waste management (SWM) are being revised as new technologies emerge and are applied in the area to achieve greater environmental, social and economic sustainability for society. To achieve our goal, two robust review protocols (Population, Intervention, Comparison, Outcome, and Context (PICOC) and Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA)) were used to systematically analyze 62 documents extracted from the Web of Science database to identify the main techniques and tools for Knowledge Discovery in Databases (KDD) and Data Mining (DM) as applied to SWM and explore the technological potential to optimize the stages of collecting and transporting waste. Moreover, it was possible to analyze the main challenges and opportunities of KDD and DM for SWM. The results show that the most used tools for SWM are MATLAB (29.7%) and GIS (13.5%), whereas the most used techniques are Artificial Neural Networks (35.8%), Linear Regression (16.0%) and Support Vector Machine (12.3%). In addition, 15.3% of the studies were conducted with data from China, 11.1% from India and 9.7% of the studies analyzed and compared data from several other countries. Furthermore, the research showed that the main challenges in the field of study are related to the collection and treatment of data, whereas the opportunities appear to be linked mainly to the impact on the pillars of sustainable development. Thus, this study portrays important issues associated with the use of KDD and DM for optimal SWM and has the potential to assist and direct researchers and field professionals in future studies.

show abstract

Fuel properties of hydrochar and pyrochar: Prediction and exploration with machine learning

Cited by 157 publications

References 38 publications

The Estimation of the Higher Heating Value of Biochar by Data-Driven Modeling

The Estimation of the Higher Heating Value of Biochar by Data-Driven Modeling

An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction

Data mining and knowledge discovery in databases for urban solid waste management: A scientific literature review

Contact Info

Product

Resources

About