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

Light Acquisition02:16

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
GIS Software, Hardware, and Sources of GIS Data01:23

GIS Software, Hardware, and Sources of GIS Data

A Geographic Information System (GIS) combines specialized software and hardware to effectively manage, analyze, and present spatial and related data. GIS software includes critical functionalities such as a user interface for easy navigation, database management tools for handling spatial and attribute data, and data retrieval features for efficient access. Analytical tools transform raw data into insights, while display functions produce maps and reports in various formats for effective...
Levels of Use of a GIS01:29

Levels of Use of a GIS

Geographic Information Systems (GIS) operate across three levels of application, each representing an increasing degree of complexity: data management, analysis, and prediction. These levels reflect the expanding functionality and versatility of GIS technology in handling spatial data for diverse purposes.Data ManagementAt its foundational level, GIS serves as a tool for data management, enabling the input, storage, retrieval, and organization of spatial data. This level is often employed in...

You might also read

Related Articles

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

Sort by
Same author

Preoperative Venous Thromboembolism in Elderly Patients with Hip Fractures: Independent Risk Factors and Interactions Between D-Dimer and Clinical Variables.

Clinical and applied thrombosis/hemostasis : official journal of the International Academy of Clinical and Applied Thrombosis/Hemostasis·2026
Same author

HDR Endorectal/Endoluminal Brachytherapy Boost in Rectal Organ Preservation: A Systematic Review and Meta-Analysis.

Cancers·2026
Same author

Early postoperative complications and patient-reported quality of life following breast-conserving surgery with intraoperative radiotherapy: A prospective cohort study.

Oncology letters·2026
Same author

Assessing P1NP/β-CTX as Potential Risk Factors Associated With Different Subtypes of Fragile Hip Fracture in Elderly Patients.

Orthopaedic surgery·2026
Same author

Comparative efficacy of intravenous, topical, and combined tranexamic acid in elderly patients with intertrochanteric fractures undergoing intramedullary nail fixation: a multicenter cohort study.

Frontiers in pharmacology·2026
Same author

Flufenamic acid fosters bacterial clearance by inhibiting Staphylococcus aureus AgrA and NLRP3 inflammasome of phagocytes.

Microbiological research·2026

Related Experiment Videos

A multi-source remote sensing and machine learning framework for maize mapping and yield estimation in fragmented

Lei Sun1,2,3, Hao Li2,3, Shangkun Li2,3,4

  • 1College of Water Resources & Civil Engineering, Hunan Agricultural University, Changsha, China.

Frontiers in Plant Science
|July 16, 2026
PubMed
Summary

Accurate maize mapping and yield prediction in smallholder farms were achieved using remote sensing and machine learning. Random Forest excelled at crop identification, while Histogram-Based Gradient Boosting improved yield estimation accuracy.

Keywords:
SHAPcrop mappingmulti-source feature fusionsmallholder farmingyield estimation

Related Experiment Videos

Area of Science:

  • Agricultural Science
  • Remote Sensing
  • Machine Learning

Background:

  • Smallholder farming systems in the Loess Plateau gully region face challenges in crop distribution mapping and yield estimation due to fragmentation.
  • Accurate agricultural data is crucial for effective management and overcoming these challenges.

Purpose of the Study:

  • To integrate multi-source remote sensing data, ancillary datasets, and machine learning for precise maize crop distribution mapping and yield estimation.
  • To compare the performance of different machine learning algorithms for maize identification and yield prediction.
  • To enhance model transparency and interpretability using SHapley Additive exPlanations (SHAP) analysis.

Main Methods:

  • Utilized Sentinel-2 spectral features, vegetation indices, and topographic variables to train and compare Random Forest (RF), Extra Trees (ET), Gradient Boosting Decision Tree (GBDT), and Histogram-Based Gradient Boosting Decision Tree (HGBDT) models for maize mapping.
  • Spatio-temporally fused Sentinel-2 optical data with ERA5-Land meteorological data.
  • Developed a maize yield estimation model using fused predictors and in-situ yield samples, followed by SHAP analysis for feature contribution assessment.

Main Results:

  • The Random Forest (RF) model demonstrated superior performance in maize identification, achieving an overall Accuracy of 0.825, Precision of 0.849, Recall of 0.933, and F1-Score of 0.889.
  • The Histogram-Based Gradient Boosting Decision Tree (HGBDT) model provided the highest accuracy for yield estimation, with R² of 0.6, RMSE of 1.07 t/ha, and MAE of 0.86 t/ha.
  • SHAP analysis successfully quantified feature contributions, enhancing model interpretability for both mapping and estimation tasks.

Conclusions:

  • The study presents an advanced methodology for accurate and interpretable crop mapping and yield estimation in complex agricultural landscapes.
  • Machine learning, particularly RF for mapping and HGBDT for yield estimation, combined with multi-source data fusion, offers effective solutions for smallholder farming systems.
  • The findings contribute to improving agricultural monitoring and decision-making in ecologically challenging regions like the Loess Plateau.