Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Methods of Medium Optimization01:28

Methods of Medium Optimization

Optimizing growth media enhances microbial proliferation and maximizes product yield. Statistical experimental design methodologies provide structured and reproducible approaches, offering progressively higher levels of robustness and efficiency.The One-Factor-at-a-Time (OFAT) MethodThe One-Factor-at-a-Time (OFAT) method involves adjusting a single variable while keeping all others constant. However, it cannot detect interactions between variables, often leading to suboptimal outcomes when...
Factors Affecting Workability01:24

Factors Affecting Workability

The workability of concrete is a critical characteristic that influences the ease of mixing, handling, and finishing the concrete. It is affected by several factors including water content, aggregate properties, and admixtures like air entrainment. Water plays a fundamental role as it lubricates the concrete mix, facilitating easier movement and placement. However, the water requirement varies depending on the texture and shape of aggregates. Finer particles and angular, rough-textured...
Multiple Regression01:25

Multiple Regression

Multiple regression assesses a linear relationship between one response or dependent variable and two or more independent variables. It has many practical applications.
Farmers can use multiple regression to determine the crop yield based on more than one factor, such as water availability, fertilizer, soil properties, etc. Here, the crop yield is the response or dependent variable as it depends on the other independent variables. The analysis requires the construction of a scatter plot...
Key Elements for Plant Nutrition02:35

Key Elements for Plant Nutrition

Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the atmosphere, the...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A wavelet and local binary pattern-based feature descriptor for the detection of chronic infection through thoracic X-ray images.

Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine·2024
Same author

Yield prediction for crops by gradient-based algorithms.

PloS one·2024
Same author

Analysis of DWT-DCT watermarking algorithm on digital medical imaging.

Journal of medical imaging (Bellingham, Wash.)·2024
Same author

AI-based wavelet and stacked deep learning architecture for detecting coronavirus (COVID-19) from chest X-ray images.

Computers & electrical engineering : an international journal·2023
Same author

Biomedical image retrieval using adaptive neuro-fuzzy optimized classifier system.

Mathematical biosciences and engineering : MBE·2022

Related Experiment Videos

Enzyme-aware soil fertility prediction using dual optimization with improved SCSO.

Pavithra Mahesh1, Rajkumar Soundrapandiyan2

  • 1School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, 632014, India.

Scientific Reports
|June 12, 2026
PubMed
Summary
This summary is machine-generated.

An improved optimization framework enhances soil fertility assessment by integrating feature selection and hyperparameter tuning. This approach boosts prediction accuracy for crop productivity using soil enzyme activity data.

Keywords:
Enzyme activityExploitationExplorationFeature selectionHyper parameter tuningPrecision agriculture

Related Experiment Videos

Area of Science:

  • Agricultural Science
  • Soil Science
  • Computational Science

Background:

  • Soil enzyme activity is crucial for crop productivity, regulating nutrient cycling and organic matter decomposition.
  • Current Machine Learning (ML) and Deep Learning (DL) models for soil fertility assessment often struggle with noisy, incomplete data and complex feature interactions, limiting their effectiveness.
  • Conventional optimization methods like Sand Cat Swarm Optimization (SCO) face challenges such as rigid exploration-exploitation transitions and premature convergence.

Purpose of the Study:

  • To develop an improved optimization framework for soil fertility assessment that integrates feature selection (FS) and hyperparameter tuning (HPT) into a unified process.
  • To enhance the utilization of biochemical indicators, specifically soil enzyme activity, for more accurate soil fertility predictions.
  • To overcome the limitations of conventional SCO methods by introducing mechanisms for improved exploration, exploitation, and convergence stability.

Main Methods:

  • Implementation of an Improved Sand Cat Swarm Optimization (Improved SCSO) framework that sequentially performs FS and HPT.
  • Incorporation of a stochastic escape-from-worst update mechanism, cosine-modulated search behavior for enhanced exploration, and a time-adaptive best-solution inheritance strategy for improved exploitation and stability.
  • Explicit inclusion of enzyme-related soil attributes and a correlation-based filtering step to select biologically meaningful and non-redundant features.

Main Results:

  • The proposed Improved SCSO framework demonstrated superior performance compared to traditional SCO-based methods.
  • Gradient Boost (GB) achieved the highest prediction accuracy of 98.48%, with hybrid models like Decision Tree (DT)+Random Forest (RF) and GB+RF also showing high performance (98.38% and 98.28%, respectively).
  • A dynamic crop mapping strategy was developed, enabling crop suitability estimation based on predicted fertility levels and enzyme activity, enhancing practical applicability.

Conclusions:

  • The developed framework significantly improves prediction accuracy and interpretability in soil fertility assessment.
  • The integration of FS and HPT within a unified optimization process, leveraging soil enzyme activity, offers an effective solution for data-driven crop recommendation.
  • The study highlights the potential of advanced optimization techniques for enhancing agricultural practices through precise soil fertility evaluation.