AI for Sustainable Farming

Abstract

Technology like the AI and IoT have been employed in farming for some time now, along with other forms of cutting-edge computer science. There has been a shift in recent years towards thinking about how to put this new technology to use. Agriculture has provided a large portion of humanity’s sustenance for thousands of years, with its most notable contribution being the widespread use of effective agricultural practices for several crop types. The advent of cutting edge IoT know-hows with the ability for monitoring agricultural ecosystems and guarantee high-quality production is underway. Smart Sustainable Agriculture continues to face formidable hurdles due to the widespread dispersion of agricultural procedures, such as the deployment4/ and administration of IoT and AI devices, sharing of data and administration, interoperability, and analysis and storage of enormous data quantities. The project aims to address pressing global challenges by promoting sustainable agriculture practices. Sustainable agriculture is characterized by its long-term viabilityand ecological compatibility, prioritizing the well-being of both humans and natural resources. It encompasses various techniques and methods that protect soil quality, conserve water resources, enhance biodiversity, and reduce greenhouse gas emissions.

Introduction

I. INTRODUCTION

Predictive analytics, a hallmark of AI, enables farmers to foresee crop yields, anticipate environmental changes, and strategically plan their agricultural activities. This  foresight not only maximizes productivity but also minimizes waste and mitigates the impact of resource scarcity. The marriage of precision agriculture and AI fosters a symbiotic relationship, where every action is finely tuned to the specific  needs  of  the  land, resulting in sustainable and eco-friendly  farming practices .

The implementation of AI applications in agriculture is accompanied by a myriad of challenges, particularly in the realm of data quality and availability. Reliable and comprehensive data, crucial for the success of AI systems, poses a significant hurdle, especially when sourcing it from remote areas. The integration of AI technologies into existing farming systems is a complex task, often marred by the reliance on traditional methods that may not seamlessly align with modern technology.

The cost associated with implementing AI systems proves to be a barrier, limiting access for small-scale farmers who may lack the financial resources. Sustainable farming practices, while essential, often demand advanced equipment and resources, further exacerbating  the  accessibility  gap   . Adaptability to local conditions, regulatory concerns, and ethical considerations, including data privacy, add layersof complexity  to the integration of AI into agriculture.

Data Quality and Availability Integration with Existing Systems Cost of Technology Resource Limitations Adaptation to Local Conditions Climate  Change  Uncertainty Data Security Scalability .

Our study holds the potential to revolutionize sustainable agriculture by leveraging AI for optimized resource management, reduced waste, and improved crop yields. This contribution directly addresses global food security, ensuring a stable and ample food supply. Sustainable farming practices supported by AI also play a crucial role in environmental preservation, mitigating the impact  of agriculture  on  the  environment and climate change             .

The economic growth resulting from enhanced farming practices contributes to rural development       . Our research promotes innovation and technology diffusion, potentially reaching traditionally  underserved  areas.  Additionally,  it  offers  academic and professional advancement opportunities while making a positive societal impact by addressing hunger, poverty, and environmental concerns.

The scope of the problem statement is extensive, encompassing critical aspects of sustainable agriculture and the integration of AI. It  addresses  the  optimization  of resource management, reduction of waste, and enhancement of crop yields through AI applications . The scope extends to global food security, aiming to ensure a stable and sufficient food supply . Environmental preservation is a significant component, focusing on mitigating the environmental impact of agriculture and tackling climate change.

The economic dimension involves improving income and profitability for farmers, contributing to rural economic development. Additionally, the study promotes innovation and technology diffusion, aiming to reach underserved areas. Its societal impact  is notable, addressing hunger, poverty, and environmental issues, aligning with global sustainability goals. The collaboration with governments, organizations, and industries underscores the comprehensive nature of the scope, fostering sustainable agriculture practices  .

Knowledge dissemination and global relevance further highlight the wide-ranging significance of the problem statement. Ultimately, the study seeks to meet the needs of future generations by ensuring access to food and resources while maintaining a healthy environment.

We can find answer to following questions by the end of project implementation.

1. How can AI-driven sustainable farming practices be adapted to diverse regional  and climatic conditions to ensure scalability and effectiveness across different agricultural landscapes?
2. What specific challenges and opportunities arise in the integration of AI technologies into traditional farming systems, particularly in areas where conventional practices still dominate?
3. How can the ethical concerns related to AI in agriculture, such as data privacy and potential impacts on traditional farming practices, be effectively addressed to  ensure responsible and sustainable implementation?
4. In what ways can the economic benefits of implementing AI in agriculture be extended to small- scale farmers, considering potential barriers such as the initial cost of technology and the needfor technical expertise?
5. How do AI models account for and adapt to the uncertainties posed by climate change, and what measures can be taken to enhance the resilience of AI-driven systems in the face of changing environmental conditions.

II. MOTIVATION

As humanity grapples with the ever-expanding global population, the imperative to ensure food security for present and future generations becomes an increasingly urgent concern. At the nexus of this challenge is the agricultural sector, a vital cornerstone of human civilization. Traditional farming methods, while resilient, are confronted with the daunting task of meeting the escalating demand  for food production, all while contending with the constraints imposed by limited resources, environmental degradation, and climate uncertainties . In response to these formidable challenges, the integration of Artificial Intelligence (AI)    into agriculture emerges as a transformative and compelling solution, driven by a confluence of pressing motivations.

A. Global Food Security Concerns: A Precarious Balancing Act

The fundamental motivation behind integrating AI into agriculture lies in addressing the  precarious balancing  act  of  global  food  security  . As the global population burgeons, estimates project a surge to over 9 billion people by 2050. This demographic surge amplifies the demand for food, imposing unprecedented stress on existing agricultural systems. The challenge extends beyond mere quantity; it encompasses the need for a stable, sufficient, and nutritionally adequate food supply that can withstandthe shocks of climate change, resource scarcity, and geopolitical fluctuations. AI, with its capacity for data-driven decision-making and precision, holds the promise of optimizing agricultural practices to enhance productivity and mitigate the looming specter  of hunger on a global scale  .

B. Shift  Towards  Sustainable  Food  Production:  Necessity  and   Responsibility

The motivation for integrating AI into agriculture is further fueled by the imperatives of sustainability. Traditional farming practices, while instrumental in feeding the world, often contribute to environmental degradation, soil erosion, and overuse of water resources      . The global consensus on the urgency of sustainable food production has catalyzed a paradigm shift in agricultural approaches  . AI, with its ability to process vast datasets and discern intricate patterns, facilitates the transition to precision agriculture—a practice finely tuned to the needs of the land .

By optimizing resource utilization, minimizing waste, and promoting eco-friendly practices, AI becomes  a linchpin in the endeavor to cultivate sustainably and responsibly, safeguarding the delicate balance between human needs and the healthof the planet.

C. Benefits of AI in Agriculture: A Multifaceted Advantage

The multifaceted advantages of  incorporating  AI  into  agriculture  serve  as  a compelling motivationfor stakeholders across the spectrum, from small-scale farmers to agribusiness conglomerates. At the forefront of these benefits is the potential for increased crop yields. AI-driven systems, armed with predictive analytics and machine learning algorithms, empower farmers to make informed decisions on  planting, irrigation,  and  pest  control,  leading  to  optimized  production  outcomes   . The resultant increase in productivity not only addresses immediate food security concerns but also contributes to economic growth by bolstering farm profitability. Reduced operational costs represent another significant benefit. AI streamlines various agricultural processes, from resource management to supply chain logistics, minimizing inefficiencies and resource wastage. This cost-effectiveness renders AI applications accessible to both large-scale and small-scale farmers, bridging economic disparities and democratizing the advantages of technological innovation.

III. LITERATURE REVIEW

Summary of research papers on smart farming/ modern farming:

Table 1

IV. PROPOSED APPROACH

A. Methods

1. Research Analysis

The research analysis employs a multifaceted approach, combining quantitative and qualitative techniques. Quantitative methods include descriptive and inferential statistics, along with machine learning      algorithms such as Decision Trees, Random Forests, and Gradient Boosting. Qualitative analysis involves semantic analysis of user feedback.

2. Data Collection Methods

Data collection is diverse, with primary data from soil sensors, weather forecast APIs, and user- generated inputs. Secondary data is sourced from agricultural databases, providing historical context.

3. Study Population

The study population comprises farmers engaging with the sustainable farming AI system. Inclusion criteria involve active participation and contribution to the system, ensuring a diverse and representative sample.

4. Tools, Materials, and Procedures

a. Tools

• Web Application: HTML, CSS, JavaScript, Django or Flask.
• Database: MySQL or PostgreSQL.
• Machine Learning Models: Python, scikit-learn.
• Clustering Algorithm: Python, scikit-learn.
• Principal Component Analysis: Python, NumPy, scikit-learn.
• Recurrent Neural Network: Python, TensorFlow or PyTorch.
• Reinforcement Learning: Python, OpenAI Gym or TensorFlow.

b. Materials

• Soil Sensors: IoT devices .
• External APIs: Google Weather API.
• CSV File: Historical data storage.

c. Procedure.

• Data Preprocessing: Cleaning, encoding, and scaling using Python and Pandas.
• Model Training: Decision Trees, Random Forests, and Gradient Boosting on historical data.
• Clustering Algorithm: K-Means clustering for soil categorization.
• Principal  Component  Analysis:  Dimensionality  reduction using  PCA.
• Recurrent Neural Network: Implementation for time series data.
• Reinforcement Learning: Continuous refinement based on user feedback.

This comprehensive methodology framework integrates diverse techniques and tools, providing a robust foundation for investigating sustainable farming through AI-driven approaches.

B. Algorithms

If we delve into the technical aspects of developing a prototype for the integration of AI into sustainable agriculture, we can explore sophisticated algorithms, neural network models, and methodologies tailored for precision farming.

1. Neural Network for Crop Prediction

In the context of crop prediction, a neural network, such as a Multilayer Perceptron (MLP), can be employed as a powerful tool for nonlinear modeling of the intricate relationships between input features and crop suitability. In highly technical terms, the neural network will serve as a complex function approximator, learning to map the high-dimensional input space, consisting of soil attributes, weather conditions, and other relevant features, to the output space representing suitable crop categories.

During the training phase, the network undergoes an iterative optimization process, adjusting weights and biases to minimize a predefined loss function, effectively fine-tuning its parameters to capture subtle patterns in the data   . Once trained, the neural network becomes an integral component of the backend system, where it processes user-provided input data, executes forward propagation to generate predictions, and seamlessly integrates with the overall decision-making process. The endpoint of this neural  network implementation lies within the predictive module of the web application, where it contributes to dynamically forecasting the most suitable crops based on the amalgamation of input features, ultimately empowering farmers with informed decision support  .

2. Clustering Algorithms for Soil Type

Clustering algorithms, like K-Means, applied for soil type classification in precision agriculture involve leveraging unsupervised learning techniques to discern inherent patterns within multivariate soil at- tribute datasets. In a technical context, these algorithms partition the high-dimensional feature space into distinct clusters, where each cluster represents a homogeneous group of soil profiles based on characteristics like pH, moisture, and acidity.

By iteratively minimizing the intra-cluster variance, K-Means optimally allocates soil samples into clusters, effectively delineating discrete soil types. The algorithm converges toward centroids that denote the average feature values within each cluster. Upon completion, soil types are discerned through the assignment of samples to the nearest centroid.  This clustering procedure, when integrated into the backend system, facilitates the automatic classification of soil profiles, optimizing agricultural decision-making processes by providing nuanced insights into soil heterogeneity for tailored crop management strategies.

3. Predictive Analytics for Crop Yield Estimation: Long Short-Term Memory (LSTM) Networks

For accurate crop yield estimation, the integration of Long Short-Term Memory (LSTM) networks within a predictive analytics framework proves instrumental  . LSTMs, a variant of recurrent neural networks (RNNs), excel in modeling sequential data and capturing temporal dependencies. By leveraging historical climate data, soil conditions, and crop growth patterns, LSTM networks can forecast future crop yields with remarkable precision. This forms the bedrock of anticipatory decision-making, empowering farmers to plan harvests and resource allocation strategically.

4. Principal Component Analysis for Feature Reduction

Principal Component Analysis (PCA) in the context of feature reduction for precision agriculture involves a linear algebraic approach to transform high-dimensional soil attribute datasets into a lower- dimensional representation, known as principal components. In highly technical terms, PCA seeks to maximize the variance captured by these components, thereby retaining the most informative aspects of the original data.

Mathematically, PCA identifies the eigenvectors and eigenvalues of the covariance matrix of the input features, serving as the basis for the principal components. The subsequent reduction in dimensionality allows for a compact yet maximally informative representation of the soil dataset. In the context of the backend system architecture, PCA becomes an integral preprocessing step, significantly reducing computational complexity and enhancing the efficiency of subsequent machine learning algorithms by focusing on the most salient aspects of the data while minimizing information loss      .

5. Recurrent Neural Network for Time Series Data (Weather Forecast)

In the context of precision agriculture, the integration of a Recurrent Neural Network (RNN) proves instrumental for handling time series data, particularly in forecasting weather conditions. An RNN, de- signed to capture temporal dependencies within sequential data, becomes a pivotal component within the back-end system. In highly technical terms, the RNN leverages its recurrent connections to retain and propagate information through time steps, allowing it to discern patterns and correlations within historical weather data.

Applied to the task of weather forecasting, the RNN sequentially processes past weather conditions to predict future states, adapting dynamically to changing patterns. This implementation, within the larger framework of the back-end, enhances the system’s predictive capabilities by seamlessly incorporating time-sensitive weather predictions into the overall dataset, thereby optimizing crop suitability predictions based on a comprehensive understanding of evolving environmental conditions  .

6. Reinforcement Learning for Feedback Mechanism

Reinforcement Learning (RL) serves as a sophisticated feedback mechanism within the sustainable farming project, intricately implemented in the back end to continually refine the machine learning  model        . In highly technical terms, RL involves an agent interacting with an environment, making decisions, and receiving feedback in the form of rewards or penalties. The agent, in this context, represents the machine learning model, and the environment encapsulates the dynamic agricultural landscape.

The RL algorithm, integrated into the system, iteratively adapts the model’s parameters through a process of trial and error, optimizing crop predictions based on historical performance metrics and user feedback. The significance of RL lies in its ability to dynamically adjust the model in response to evolving user requirements and changing environmental factors, contributing to a continual enhancement of prediction accuracy . The endpoint of this RL implementation resides within the feedback loop of the back end, forming a closed- loop system where the model refines itself iteratively, ensuring an adaptive and responsive approach to crop suitability predictions.

V. MODELLING

A. Decision Tree and Random Forest

In the realm of sustainable farming, employing advanced technologies such as Decision Trees and Random Forests in predictive modeling holds significant promise [1].  A Decision Tree, a fundamental component of this approach, operates by recursively partitioning data based on feature conditions, forming a hierarchical structure that culminates in leaf nodes representing predictions  .

In the context of crop suitability prediction, a Decision Tree might make decisions based on soil pH, moisture levels, and other relevant factors. On the other hand, the Random Forest algorithm extends this concept by constructing an ensemble of Decision Trees, each trained on a subset of the dataset. By aggregating the predictions from multiple trees, the Random Forest minimizes overfitting and enhances the robustness of the model.

This proves invaluable in the dynamic and multifaceted landscape of sustainable farming, where intricate relationships between soil characteristics, weather conditions, and crop types demanda nuanced predictive framework . Incorporating these machine learning techniques not only facilitates accurate crop recommendations for farmers but also contributes to the ongoing evolution of precision agriculture, paving the way for a more sustainable and efficient future in agricultural practices                                                                                                                                         .

B. Gradient Boosting

Within the ambit of sustainable farming predictive modeling, Gradient Boosting emerges as a sophisticated technique that leverages an ensemble of weak learners to create a robust and accurate predictivemodel . Specifically, Gradient Boosting builds successive decision trees, each focused on correcting the errors of its predecessor. It does so by assigning higher weights to misclassified instances, effectively emphasizing the nuances in the dataset.

This iterative learning process, driven by the  minimization  of  a  predefined  loss function, ensures that the model continually refines its predictions, achieving heightened precision  over  successive  iterations  . The adaptive nature of Gradient Boosting renders it particularly adept at capturing intricate relationships between soil attributes, weather conditions, and crop suitability.

Through its nuanced optimization approach, Gradient Boosting stands as a powerful tool in the arsenal of sustainable farming AI , offering a technical framework that not only enhances prediction accuracy but also contributes to the evolution of precision agriculture methodologies.

VI. RESULT AND DISCUSSION

In today's fast-changing world, farming is facing big challenges. As more people need food, the way we've always farmed might not be enough. Climate change is making things even harder. We need to find new ways to grow food that are good for the environment and can handle unexpected weather. This means using more technology and special computer programs, like artificial intelligence (AI) [4]. AI can help us predict what might happen on the farm, use less water and energy, and do tasks on their own. It's like having a smart helper on the farm. By using AI, we can make farming better for the planet and for the people who need the food [1] [13] [15].

The importance of supportive policies and practices to facilitate the widespread adoption of AI in agriculture. Policymakers need to establish regulatory frameworks that promote ethical AI use and incentivize investment in AI solutions through subsidies and tax breaks. Improving rural infrastructure and providing training to farmers are essential to ensure equitable access to AI technologies. Addressing affordability concerns and building farmers' technical capacity will be key in overcoming barriers to adoption.

Additionally, clear guidelines on data privacy and security are necessary to foster trust among farmers [5]. Collaborative efforts involving government, technology providers, and agricultural stakeholders are crucial for driving AI adoption and realizing its potential for sustainable farming practices [2].

VII. OUTCOMES

1. Increased understanding of global economic trends: By analyzing vast amounts of economic data,researchers can gain a deeper understanding of the underlying forces that drive global economic growth, inflation, unemployment, and other key economic indicators. This can help policymakers, businesses, and individuals make informed decisions about their investments, spending, and economic strategies.
2. Development of predictive models for future economic performance: Machine learning and other advanced analytics techniques can be used to develop predictive models that forecast future economic indicators, such as GDP growth, inflation rates, and unemployment  rates. This can help businesses and governments plan for potential economic shocks, such as recessions or financial crises.
3. Identification of emerging economic opportunities and risks: Analyzing data on global trade, investment, and demographics can help businesses identify new markets and opportunities for growth, while also identifying potential risks associated with changing economic conditions.
4. Enhanced decision-making for policymakers: Economic data analytics can provide policymakers with valuable insights into the impact of their policies on various sectors of the  economy  . By understanding the potential consequences of their decisions, policymakers can make more informed choices that promote economic growth and stability.
5. Improved understanding of economic inequality and poverty: Data analytics can help researchers identify patterns and trends in economic inequality and poverty, both within countries and acrossthe globe. This can help policymakers target interventions to reduce economic disparities and improve the lives of marginalized populations.
6. Enhanced transparency and accountability: Making economic data more accessible and trans- parent can promote accountability and transparency among governments, businesses, and other organizations. This can foster a more equitable and accountable global economic system.

Conclusion

In conclusion, designing a system for deriving insights from global economic data and identifyingtrends is a multifaceted challenge that requires a well-thought-out architecture and integration of various components. The complexities of the global economic landscape demand a robust system that can handle diverse data sources, and large volumes of information, and provide timely and accurate insights. In summary, a well-designed architecture that encompasses data management, processing, analytics, visualization, and security is essential for deriving meaningful insights from global economic data. The success of such a system lies in its ability to provide actionable intelligence to decision- makers, enabling them to navigate the complexities of the global economy with confidence. 1) Early warning systems for economic crises. By analyzing large amounts of data, researchers can identify early warning signs of economic problems, such as rising debt levels or declining productivity. This information can be used to prevent or mitigate the impact of these crises. 2) Investment advice. Investors can use global economic data to identify countries, sectors, and companies that are likely to perform well in the future. This information can help them make better investment decisions. 3) Risk management. Businesses can use global economic data to assess the risks they face, suchas changes in currency exchange rates or interest rates. This information can help them develop strategies to mitigate these risks. 4) Policymaking. Governments can use global economic data to inform their economic policies.For example, they can use this data to assess the impact of trade agreements or to design fiscal stimulus packages. 5) Sustainability planning. Organizations can use global economic data to assess the impact of their activities on the environment and to develop more sustainable business practices

References

[1] Dongyang Huo, Asad Waqar Malik, Sri Devi Ravana, Anis Ur Rahman, Ismail Ahmedy, “Mapping smart farming: Addressing agricultural challenges in data-driven era, Renewable and Sustainable Energy Reviews”, 2024. https://doi.org/10.1016/j.rser.2023.113858 [2] H. Rahmani et al, “Next- Generation IoT Devices: Sustainable Eco-Friendly Manufacturing, Energy Harvesting, and Wireless Connectivity”, 2023. https://doi.org/10.1109/JMW.2022.3228683 [3] Subudhi, S., Dabhade, R. G., Shastri, R., Gundu, V., Vignesh, G. D., & Chaturvedi, “Empowering sustainable farming practices with AI-enabled interactive visualization of hyper- spectral imaging data”, 2023. https://doi.org/10.1016/j.measen.2023.100935 [4] A. A. AlZubi and K. Galyna, “Artificial Intelligence and Internet of Things for Sustainable Farming and Smart Agriculture”, 2023. https://doi.org/10.1109/ACCESS.2023.3298215 [5] Santoshi Rudrakar, Parag Rughani, “IoT based Agriculture (Ag-IoT): A detailed study on Architecture, Security and Forensics, Information Processing in Agriculture”, 2023. https://doi.org/10.1016/j.inpa.2023.09.002 [6] H. Rahmani et al., “Next-Generation IoT Devices: Sustainable Eco-Friendly Manufacturing, Energy Harvesting, and Wireless Connectivity”, 2023. https://doi.org/10.1109/JMW.2022.3228683 [7] Dhanaraju, M., Chenniappan, P., Ramalingam, K., Pazhanivelan, S., & Kaliaperumal,”Smart Farming: Internet of Things (IoT)-Based Sustainable Agriculture”, 2022. https://doi.org/10.3390/agriculture12101745 [8] Quy, V. K., Hau, N. V., Anh, D. V., Quy, N. M., Ban, N. T., Lanza, S., Randazzo, G., & Muzirafuti, “IoT-Enabled Smart Agriculture: Architecture, Applications, and Challenges, Applied Sciences”, 2022. https://doi.org/10.3390/app12073396 [9] Dhanaraju, M., Chenniappan, P., Ramalingam, K., Pazhanivelan, S., & Kaliaperumal. “Smart Farming: Internet of Things (IoT)-Based Sustainable Agriculture”, 2022. https://doi.org/10.3390/agriculture12101745 [10] N obrega, L., Gon calves, P., Pedreiras, P., & Pereira. “An IoT-Based Solution for Intelligent Farming”, 2019. https://doi.org/10.3390/s19030603 [11] Roux, J., Escriba, C., Fourniols, J.-Y., & Soto-Romero. “A New Bi-Frequency Soil Smart Sensing Moisture and Salinity for Connected Sustainable Agriculture”, 2019. https://doi.org/10.4236/jst.2019.93004 [12] Farooq, M. S., Riaz, S., Abid, A., Abid, K., & Naeem. “A Survey on the Role of IoT in Agriculture for the Implementation of Smart Farming”, 2019. https://doi.org/10.1109/ACCESS.2019.2949703 [13] Chukkapalli, S. S. L., et al. “Ontologies and Artificial Intelligence Systems for then Cooperative Smart Farming Ecosystem”, 2020. https://doi.org/10.1109/ACCESS.2020.3022763 [14] Srisruthi, S., Swarna, N., Ros, G. M. S., & Elizabeth. “Sustainable agriculture using eco- friendly and energy-efficient sensor technology”, 2016. https://doi.org/10.1109/RTEICT.2016.7808070 [15] Quy, V. K., Hau, N. V., Anh, D. V., Quy, N. M., Ban, N. T., Lanza, S., Randazzo, G., & Muzi-rafuti. “IoT-Enabled Smart Agriculture: Architecture, Applications, and Challenges”, 2022. https://doi.org/10.3390/app12073396 [16] Subudhi, S., Dabhade, R. G., Shastri, R., Gundu, V., Vignesh, G. D., & Chaturvedi. \"Empowering sustainable farming practices with AI-enabled interactive visualization of hyperspectral imaging data\", 2023. https://doi.org/10.1016/j.measen.2023.100935 [17] Rajeswari, K. Suthendran. “Advanced Decision Tree (ADT) classification model for agricultural data analysis on cloud, Computers and Electronics in Agriculture”, 2019. https://doi.org/10.1016/j.compag.2018.12.013 [18] Vasileios Moysiadis, Panagiotis Sarigiannidis, Vasileios Vitsas, Adel Khelifi. “Smart Farming in Europe”, 2021. https://doi.org/10.1016/j.cosrev.2020.100345 [19] L. Barreto and A. Amaral, “Smart Farming: Cyber Security Challenges”, 2018. https://doi.org/10.1109/IS.2018.8710531 [20] Sjaak Wolfert, Lan Ge, Cor Verdouw, Marc-Jeroen Bogaardt. “Big Data in Smart Farming – A review”, 2017. https://doi.org/10.1016/j.agsy.2017.01.023 [21] M. S. Mekala and P. Viswanathan, “A Survey: Smart agriculture IoT with cloud computing”, 2017. https://doi.org/10.1109/ICMDCS.2017.8211551 [22] Othaman, N. N. C., MN Md Isa, R. Hussin, S. M. M. S. Zakaria, and M. M. Isa. “IoT Based Soil Nutrient Sensing System for Agriculture Application.”, 2021. [23] Kavita Jhajhariaa, Pratistha Mathura, Sanchit Jaina, Sukriti Nijhawan, “Crop Yield Prediction using Machine Learning and Deep Learning Techniques”, 2023. https://doi.org/10.1016/j.procs.2023.01.023 [24] Sundari V, Anusree M, Swetha U and Divya Lakshmi R, “Crop recommendation and yield prediction using machine learning algorithms”, 2022. https://doi.org/10.30574/wjarr.2022.14.3.0581 [25] Ishwarya R, Nagapooja BN, Raghavi R, Soundarya K, Prof. Chitra C, “Crop Yield Prediction Using Machine Learning Algorithm”, 2022. [26] S. P. Raja, Barbara Sawicka, Zoran Stamenkovic, And G. Mariammal, “Crop Prediction Based on Characteristics of the Agricultural Environment Using Various Feature Selection Techniques and Classifiers”, 2022. https://doi.org/10.1109/ACCESS.2022.3154350 [27] Namgiri Suresh, N.V.K.Ramesh, Syed Inthiyaz, P. Poorna Priya, Kurra Nagasowmika, Kota.V.N.Harish Kumar, Mashkoor Shaik and 2B. N. K. Reddy, “Crop Yield Prediction Using Random Forest Algorithm”, 2021. https://doi.org/10.1109/ICACCS51430.2021.9441871 [28] D. J. Reddy and M. R. Kumar, “Crop Yield Prediction using Machine Learning Algorithm”, 2021. https://doi.org/10.1109/ICICCS51141.2021.9432236 [29] Khadijeh Alibabaei, Pedro D. Gasper, Tania M. Lima. “Cop Yield Estimation Using Learning Based on Climate Big Data and Irrigation Scheduling”, 2021. https://doi.org/10.3390/en14113004 [30] Madhuri Shripathi Rao, Arushi Singh , N.V. Subba Reddy and Dinesh U Acharya, “Crop prediction using machine learning”, 2021. https://doi.org/10.1088/1742- 6596/2161/1/012033 [31] Shilpa Mangesh Pande, Dr. Prem Kumar Ramesh, Anmol, B.R Aishwarya, Karuna Rohilla, Kumar Shaurya, “Crop Recommender System Using Machine Learning Approach”, 2021. https://doi.org/10.1109/ICCMC51019.2021.9418351 [32] P. S. Nishant, P. Sai Venkat, B. L. Avinash and B. Jabber, “Crop Yield Prediction based on Indian Agriculture using Machine Learning”, 2020. https://doi.org/10.1109/INCET49848.2020.9154036 [33] Saeed Khaki, Lizhi Wang, “Crop Yield Prediction using Deep Neural Network”, 2019. https://doi.org/10.3389/fpls.2019.00621 [34] S Iniyan, V Akhil Varma, Ch Teja Naidu. “Crop yield prediction using machine learning techniques”, 2023. https://doi.org/10.1016/j.advengsoft.2022.103326

Copyright

Copyright © 2024 Prof. Arti Sonawane, Sahil Shrivastava , Yash Chinawale, Ojas Surpatne, Jatin Zade . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.