Crop Prediction Model Using Machine Learning Algorithms

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(16), P. 9288 - 9288

Published: Aug. 16, 2023

Machine learning applications are having a great impact on the global economy by transforming data processing method and decision making. Agriculture is one of fields where significant, considering crisis for food supply. This research investigates potential benefits integrating machine algorithms in modern agriculture. The main focus these to help optimize crop production reduce waste through informed decisions regarding planting, watering, harvesting crops. paper includes discussion current state agriculture, highlighting key challenges opportunities, presents experimental results that demonstrate changing labels accuracy analysis algorithms. findings recommend analyzing wide-ranging collected from farms, incorporating online IoT sensor were obtained real-time manner, farmers can make more verdicts about factors affect growth. Eventually, technologies transform agriculture increasing yields while minimizing waste. Fifteen different have been considered evaluate most appropriate use new feature combination scheme-enhanced algorithm presented. show we achieve classification 99.59% using Bayes Net 99.46% Naïve Classifier Hoeffding Tree These will indicate an increase rates effective cost leading resilient infrastructure sustainable environments. Moreover, this study also future detect diseases early, efficiency, prices when world experiencing shortages.

Language: Английский

---

Enhancing precision agriculture: A comprehensive review of machine learning and AI vision applications in all-terrain vehicle for farm automation

Smart Agricultural Technology, Journal Year: 2024, Volume and Issue: 8, P. 100483 - 100483

Published: June 4, 2024

The automation of all-terrain vehicles (ATVs) through the integration advanced technologies such as machine learning (ML) and artificial intelligence (AI) vision has significantly changed precision agriculture. This paper aims to analyse develop trends provide comprehensive knowledge current state ATV-based agriculture future possibilities ML AI. A bibliometric analysis was conducted network diagram with keywords taken from previous publications in domain. review comprehensively analyses potential transforming farming operations tasks deployment vehicles. research extensively how methods have influenced several aspects agricultural activities, planting, harvesting, spraying, weeding, crop monitoring, others. AI systems are being researched for their ability enhance precise prompt decision-making ATV-driven automation. These been thoroughly tested show they can improve yield, reducing overall investment, make more efficient. Examples include learning-based seeding accuracy, AI-enabled health use accurate pesticide application. assessment examines challenges data privacy problems scalability constraints, along advancements prospects field. will assist researchers practitioners making well-informed judgments regarding practices that efficient, sustainable, technologically robust.

Language: Английский

---

Prediction of winter wheat yield and dry matter in North China Plain using machine learning algorithms for optimal water and nitrogen application

Agricultural Water Management, Journal Year: 2023, Volume and Issue: 277, P. 108140 - 108140

Published: Jan. 5, 2023

Accurate prediction of crop yield and dry matter as well optimized water nitrogen management can favor rational decision-making for farming systems. Combining high-performance computing with innovative technologies big data processing, machine learning (ML) advances data-intensive science provides an important supporting frame prediction. This paper evaluated the performance five ML algorithms, including linear regression (LR), decision tree (DT), support vector (SVM), ensemble (EL), Gaussian process (GPR), winter wheat (Triticum aestivum L.) using collected from previous studies conducted within last twenty years in North China Plain (NCP). In addition, were explored best algorithm, while polynomial functions proposed that could describe relationship application matter. Results confirmed GPR model outperformed all other models predicting (R2 = 0.87) 0.86) wheat. The errors maximum 5.8 % 1.1 %, respectively. NCP be predicted by functions, optimal obtained. results provide insight into site-specific management.

Language: Английский

---

The artificial intelligence-based agricultural field irrigation warning system using GA-BP neural network under smart agriculture

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(1), P. e0317277 - e0317277

Published: Jan. 17, 2025

This work explores an intelligent field irrigation warning system based on the Enhanced Genetic Algorithm—Backpropagation Neural Network (EGA-BPNN) model in context of smart agriculture. To achieve this, flow prediction agricultural fields is chosen as research topic. Firstly, BPNN principles are studied, revealing issues such sensitivity to initial values, susceptibility local optima, and sample dependency. address these problems, a genetic algorithm (GA) adopted for optimizing BPNN, EGA-BPNN used predict fields. Secondly, can overcome optimization overfitting problems traditional through global search ability GA. Moreover, it suitable task with complex environmental factors Finally, comparative experiments compare accuracy using single dual water level models respectively. The results reveal that number nodes hidden layer increases, model’s Mean Squared Error (MSE) Relative (RE) show decreasing trend, indicating improvement accuracy. When increases from 6 16, MSE decreases 4.53×10 −4 3.68×10 2.38×10 1.66×10 , Under standalone absolute relative error 1.09%. In contrast, achieves significantly lower mean 0.41% single-flow prediction, demonstrating superior performance. Furthermore, compared exhibits 2.11 reduction MSE, further emphasizing positive impact introducing GA outcomes contribute more accurate resource planning management, providing reliable basis decision-making.

Language: Английский

---

Machine Learning and Deep Learning Paradigms: From Techniques to Practical Applications and Research Frontiers

Computers, Journal Year: 2025, Volume and Issue: 14(3), P. 93 - 93

Published: March 6, 2025

Machine learning (ML) and deep (DL), subsets of artificial intelligence (AI), are the core technologies that lead significant transformation innovation in various industries by integrating AI-driven solutions. Understanding ML DL is essential to logically analyse applicability identify their effectiveness different areas like healthcare, finance, agriculture, manufacturing, transportation. consists supervised, unsupervised, semi-supervised, reinforcement techniques. On other hand, DL, a subfield ML, comprising neural networks (NNs), can deal with complicated datasets health, autonomous systems, finance industries. This study presents holistic view technologies, analysing algorithms application’s capacity address real-world problems. The investigates application which techniques implemented. Moreover, highlights latest trends possible future avenues for research development (R&D), consist developing hybrid models, generative AI, incorporating technologies. aims provide comprehensive on serve as reference guide researchers, industry professionals, practitioners, policy makers.

Language: Английский

---

A Structured and Methodological Review on Vision-Based Hand Gesture Recognition System

Journal of Imaging, Journal Year: 2022, Volume and Issue: 8(6), P. 153 - 153

Published: May 26, 2022

Researchers have recently focused their attention on vision-based hand gesture recognition. However, due to several constraints, achieving an effective vision-driven recognition system in real time has remained a challenge. This paper aims uncover the limitations faced image acquisition through use of cameras, segmentation and tracking, feature extraction, classification stages various camera orientations. looked at research systems from 2012 2022. Its goal is find areas that are getting better those need more work. We used specific keywords 108 articles well-known online databases. In this article, we put together collection most notable works related suggest different categories for recognition-related with subcategories create valuable resource domain. summarize analyze methodologies tabular form. After comparing similar types field, drawn conclusions based our findings. Our also how well recognized gestures terms accuracy. There wide variation identification accuracy, 68% 97%, average being 86.6 percent. The considered comprise multiple text interpretations complex non-rigid characteristics. comparison current research, unique it discusses all techniques.

Language: Английский

---

Multi-Stage Corn Yield Prediction Using High-Resolution UAV Multispectral Data and Machine Learning Models

Agronomy, Journal Year: 2023, Volume and Issue: 13(5), P. 1277 - 1277

Published: April 28, 2023

Timely and cost-effective crop yield prediction is vital in management decision-making. This study evaluates the efficacy of Unmanned Aerial Vehicle (UAV)-based Vegetation Indices (VIs) coupled with Machine Learning (ML) models for corn (Zea mays) at vegetative (V6) reproductive (R5) growth stages using a limited number training samples farm scale. Four agronomic treatments, namely Austrian Winter Peas (AWP) (Pisum sativum L.) cover crop, biochar, gypsum, fallow sixteen replications were applied during non-growing season to assess their impact on following yield. Thirty different variables (i.e., four spectral bands: green, red, red edge, near-infrared twenty-six VIs) derived from UAV multispectral data collected V6 R5 utility prediction. Five ML algorithms including Linear Regression (LR), k-Nearest Neighbor (KNN), Random Forest (RF), Support Vector (SVR), Deep Neural Network (DNN) evaluated One-year experimental results treatments indicated negligible overall Red canopy chlorophyll content index, edge absorption ratio green normalized difference vegetation band, index among most suitable predicting The SVR predicted Coefficient Determination (R2) Root Mean Square Error (RMSE) 0.84 0.69 Mg/ha 0.83 1.05 stage, respectively. KNN achieved higher accuracy AWP (R2 = RMSE 0.64 1.13 R5) gypsum treatment 0.61 1.49 0.80 1.35 R5). DNN biochar 0.71 1.08 0.74 1.27 For combined (AWP, fallow) treatment, produced accurate an R2 0.36 1.48 0.41 1.43 R5. Overall, treatment-specific was more than treatment. Yield accurately other regardless model used. outperformed Yields similar both stages. Thus, this demonstrated that VIs can be used multi-stage scale, even data.

Language: Английский

---

Deep-learning-based counting methods, datasets, and applications in agriculture: a review

Precision Agriculture, Journal Year: 2023, Volume and Issue: 24(5), P. 1683 - 1711

Published: June 24, 2023

Language: Английский

---

Machine learning technology for early prediction of grain yield at the field scale: A systematic review

Computers and Electronics in Agriculture, Journal Year: 2023, Volume and Issue: 207, P. 107721 - 107721

Published: March 2, 2023

Language: Английский

---

Automated Estimation of Crop Yield Using Artificial Intelligence and Remote Sensing Technologies

Bioengineering, Journal Year: 2023, Volume and Issue: 10(2), P. 125 - 125

Published: Jan. 17, 2023

Agriculture is the backbone of any country, and plays a viable role in total gross domestic product (GDP). Healthy fruitful crops are immense importance for government to fulfill food requirements its inhabitants. Because land diversities, weather conditions, geographical locations, defensive measures against diseases, natural disasters, monitoring with human intervention becomes quite challenging. Conventional crop classification yield estimation methods ineffective under unfavorable circumstances. This research exploits modern precision agriculture tools enhanced remote estimation, types by proposing fuzzy hybrid ensembled method using sensory data. The architecture enhances pooled images neighborhood spatial filtering, scaling, flipping, shearing, zooming. study identifies optimal weights strongest candidate classifiers adopting bagging strategy. We augmented imagery datasets achieve an unbiased between different types, including jute, maize, rice, sugarcane, wheat. Further, we considered flaxseed, lentils, wheat on publicly available provided Food Organization (FAO) United Nations Word Bank DataBank. ensemble outperformed individual type average 13% 24% compared highest gradient boosting lowest decision tree methods, respectively. Similarly, observed that predictor multivariate regressor, random forest, comparatively lower mean square error value years 2017 2021. proposed supports embedded devices, where devices can adopt lightweight algorithm, such as MobilenetV2. significantly reduce processing time overhead large set images.

Language: Английский

---