![Sample our Engineering & Technology journals, sign in here to start your access, latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5933/TOC-Subject-Sample-2021-Engineering-Tech.jpg"})
ABSTRACT
The application of biomass, as an energy resource, depends on four main steps of production, pre-treatment, bio-refinery, and upgrading. This work reviews Machine Learning applications in the biomass production step with focusing on agriculture crops. By investigating numerous related works, it is concluded that there is a considerable reviewing gap in collecting the applications of Machine Learning in crop biomass production. To fill this gap by the current work, the origin of biomass raw materials is explained, and the application of Machine Learning in this section is scrutinized. Then, the kinds and resources of biomass as well as the role of machine learning in these fields are reviewed. Meanwhile, the sustainable production of farming-origin biomass and the effective factors in this issue are explained, and the application of Machine Learning in these areas are surveyed. Summarily, after analysis of numerous papers, it is concluded that Machine Learning and Deep Learning are widely utilized in crop biomass production areas to enhance the crops production quantity, quality, and sustainability, improve the predictions, decrease the costs, and diminish the products losses. According to the statistical analysis, in 19% of the studies conducted about the application of Machine Learning and Deep Learning in crop biomass raw materials, Artificial Neural Network (ANN) algorithm has been applied. Afterward, the Random Forest (RF) and Super Vector Machine (SVM) are the second and third most-utilized algorithms applied in 17% and 15% of studies, respectively. Meanwhile, 26% of studies focused on the applications of Machine Learning and Deep Learning in the sugar crops. At the second and third places, the starchy crops and algae with 23% and 21% received more attention of researchers in the utilization of Machine Learning and Deep Learning techniques.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Abbreviations
| ML | = | Machine Learning |
| DL | = | Deep Learning |
| AI | = | Artificial Intelligence |
| ANFIS | = | Adaptive Network Fuzzy Inference System |
| SVM | = | Super Vector Machine |
| NB | = | Naive Bayes |
| KNN | = | K-nearest Neighbor |
| DT | = | Decision Tree |
| RF | = | Random Forest |
| ALO | = | Antlion optimization |
| ANN | = | Artificial Neural Network |
| GAM | = | Generalized Additive Model |
| RNN | = | Recurrent Neural Network |
| MLR | = | Multiple Linear Regression |
| FRBS | = | Fuzzy Rule-based Systems |
| LDA | = | Linear Discriminant Analysis |
| NIR | = | Near Infrared |
| RBF | = | Radial Basis Function |
| SPA | = | Successive Projection Algorithm |
| LRM | = | Linear Regression Model |
| CRBM | = | Conditional Restricted Boltzmann Machine |
| SMR | = | Stepwise Multiple Regression |
| ELM | = | Extreme Learning Machine |
| SA | = | Simulated Annealing |
| IMVO | = | Improved Multi Verse Optimizer |
| EMPA | = | Extended Marine Predators Algorithm |
| LSTM | = | Long Short Term Memory |
| CNN | = | Convolutional Neural Network |
| MLP | = | Multilayer Perceptron |
| CO2 | = | Carbon Dioxide |
| GP | = | Gaussian Process |
| DNN | = | Deep Neural Network |
| LR | = | Logistics Regression |
| GBDT | = | Gradient Boosting Decision Tree |
| AdaBoost | = | Adaptive boosting |
| GBO | = | Gradient-Based Optimization |
| XGBoost | = | Extreme Gradient Boosting |
| PGM | = | Probabilistic Graphical Models |
| PSO | = | Particle Swarm Optimization |
| BNN | = | Bayesian Neural Network |
| PLS-DA | = | Partial Least Squares Discriminant Analysis |
| BRT | = | Boosted Regression Tree |
| GBM | = | Generalized Boosted Model |
| PLS | = | Partial Least Squares |
| MARS | = | Multivariate Adaptive Regression Splines |
| CARS | = | Competitive Adaptive Reweighted Sampling |
| SVR | = | Supper Vector Regression |
| PCA | = | Principal Component Analysis |
| GLM | = | Generalized Linear Model |
| GWO | = | Grey Wolf Optimization |
| MOA | = | Mayfly Optimization Algorithm |
| SAMOA | = | Simulated Annealing (SA) algorithm integrated with Mayfly Optimization Algorithm (MOA) |
| CRFOA | = | Chaos Red Fox Optimization Algorithm |
Additional information
Notes on contributors
Wei Peng
Dr. Wei Peng, as the Assistant Professor at Uiversity of Regina with Research Interests of Development and application of Simulation, Modeling, and Optimization, techniques for dealing with uncertainty in Environmental Engineering, Sustainable Engineering, Industrial Engineering, Process Engineering, and Management.
Omid Karimi Sadaghiani
Dr. Omid Karimi Sadagiani, as the Post-Doc fellow at University of Regina, with expertise in Energy Engineering.