Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Machine Learning for Dynamic Management Zone in Smart Farming

Chamil Kulatunga, Sahraoui Dhelim, Tahar Kechadi

TL;DR

The paper addresses delineating dynamic management zones in precision agriculture by integrating historical yield data, topography, soil texture, and satellite-derived NDVI. It combines Moran's LISA clustering for yield region identification with Geographically Weighted Regression to reveal spatially varying drivers, supplemented by yield frequency maps that capture persistent versus incidental field issues. The methodology leverages a 10 m base grid, multi-year yield maps, and Sentinel-2 vegetation indices to support site-specific decisions and variable-rate nitrogen applications. This approach advances sustainable intensification by enabling more accurate zoning and targeted management based on yield potential and stability patterns observed over time.

Abstract

Digital agriculture is growing in popularity among professionals and brings together new opportunities along with pervasive use of modern data-driven technologies. Digital agriculture approaches can be used to replace all traditional agricultural system at very reasonable costs. It is very effective in optimising large-scale management of resources, while traditional techniques cannot even tackle the problem. In this paper, we proposed a dynamic management zone delineation approach based on Machine Learning clustering algorithms using crop yield data, elevation and soil texture maps and available NDVI data. Our proposed dynamic management zone delineation approach is useful for analysing the spatial variation of yield zones. Delineation of yield regions based on historical yield data augmented with topography and soil physical properties helps farmers to economically and sustainably deploy site-specific management practices identifying persistent issues in a field. The use of frequency maps is capable of capturing dynamically changing incidental issues within a growing season. The proposed zone management approach can help farmers/agronomists to apply variable-rate N fertilisation more effectively by analysing yield potential and stability zones with satellite-based NDVI monitoring.

Machine Learning for Dynamic Management Zone in Smart Farming

TL;DR

The paper addresses delineating dynamic management zones in precision agriculture by integrating historical yield data, topography, soil texture, and satellite-derived NDVI. It combines Moran's LISA clustering for yield region identification with Geographically Weighted Regression to reveal spatially varying drivers, supplemented by yield frequency maps that capture persistent versus incidental field issues. The methodology leverages a 10 m base grid, multi-year yield maps, and Sentinel-2 vegetation indices to support site-specific decisions and variable-rate nitrogen applications. This approach advances sustainable intensification by enabling more accurate zoning and targeted management based on yield potential and stability patterns observed over time.

Abstract

Digital agriculture is growing in popularity among professionals and brings together new opportunities along with pervasive use of modern data-driven technologies. Digital agriculture approaches can be used to replace all traditional agricultural system at very reasonable costs. It is very effective in optimising large-scale management of resources, while traditional techniques cannot even tackle the problem. In this paper, we proposed a dynamic management zone delineation approach based on Machine Learning clustering algorithms using crop yield data, elevation and soil texture maps and available NDVI data. Our proposed dynamic management zone delineation approach is useful for analysing the spatial variation of yield zones. Delineation of yield regions based on historical yield data augmented with topography and soil physical properties helps farmers to economically and sustainably deploy site-specific management practices identifying persistent issues in a field. The use of frequency maps is capable of capturing dynamically changing incidental issues within a growing season. The proposed zone management approach can help farmers/agronomists to apply variable-rate N fertilisation more effectively by analysing yield potential and stability zones with satellite-based NDVI monitoring.
Paper Structure (13 sections, 2 equations, 11 figures, 5 tables)

This paper contains 13 sections, 2 equations, 11 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Study Area and Data Formation
  4. Yield Data
  5. Yield Frequency Map
  6. Satellite Imagery
  7. Vegetation Indexes
  8. Geographically Weighted Regression
  9. Software architecture and capabilities
  10. Yield clustering and frequency maps
  11. Soil properties analysis
  12. Spatial and topographic properties
  13. Conclusion

Figures (11)

  • Figure 1: Combined temporal-spatial yield map pre-processing
  • Figure 2: Yield Frequency Map
  • Figure 3: Cloud-free NDVI images
  • Figure 4: Spatially Varying Coefficients with NDVI and FM
  • Figure 5: Frequency map and zone monitoring
  • ...and 6 more figures