Jadwal Sholat

Memuat jadwal sholat…

Ilmu Komputer & AI editorial

Open AccessOA2023

Machine Learning Applications in Agriculture: Current Trends, Challenges, and Future Perspectives

This systematic review explores Machine Learning applications in agriculture, covering crop, water, soil, and animal management, and discusses impacts, challenges, and future directions.
S. Araújo; Ricardo Silva Peres; J. C. Ramalho; F. Lidon; José Barata· Agronomy· 2023· DOI 10.3390/agronomy13122976

The core problem

The agricultural sector is undergoing a transformation towards Agriculture 4.0, driven by technologies such as the Internet of Things (IoT), sensors, robotics, Artificial Intelligence (AI), Machine Learning (ML), Big Data, and Cloud Computing. Strategic investments in technological research are essential for improving agricultural productivity and sustainability. This systematic literature review aims to explore the usage of ML in agriculture, identify its foremost applications, assess impacts and outcomes, and highlight challenges associated with its integration. The review follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to ensure a rigorous and transparent approach.

Innovation

The review employs the PRISMA methodology for systematic literature reviews. The process includes:

1. **Identification**: Searching multiple databases for relevant studies on ML in agriculture.
2. **Screening**: Applying inclusion and exclusion criteria to filter studies.
3. **Eligibility**: Assessing full-text articles for eligibility.
4. **Inclusion**: Synthesizing findings from included studies.

The methodology ensures a comprehensive and unbiased collection of literature. The review focuses on ML applications in crop, water, soil, and animal management, among others.

Introduction
The agricultural sector is undergoing a transformation towards Agriculture 4.0, driven by technologies such as the Internet of Things (IoT), sensors, robotics, Artificial Intelligence (AI), Machine Learning (ML), Big Data, and Cloud Computing. Strategic investments in technological research are essential for improving agricultural productivity and sustainability. This systematic literature review aims to explore the usage of ML in agriculture, identify its foremost applications, assess impacts and outcomes, and highlight challenges associated with its integration. The review follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to ensure a rigorous and transparent approach.

Why it matters

The adoption of ML in agriculture brings substantial impacts and outcomes, such as increased productivity, optimized resource utilization, and improved sustainability. However, several challenges hinder its integration:

- **Data Availability and Quality**: Lack of large, high-quality datasets for training ML models.
- **Infrastructure and Connectivity**: Limited internet and sensor infrastructure in rural areas.
- **Technical Expertise**: Shortage of skilled personnel to develop and maintain ML systems.
- **Cost and Scalability**: High initial investment and scalability issues for small farms.
- **Ethical and Privacy Concerns**: Data ownership and privacy issues.

Addressing these challenges requires collaborative efforts from researchers, policymakers, and industry stakeholders. Future research should focus on developing robust, scalable, and cost-effective ML solutions tailored to agricultural needs.

Who should read this

Pembaca Research Digest dan praktisi rumpun ini.

Opening member content…