Comparative Analysis Between Sentinel-2 And Proximal Sensors to Study the Spatial Distribution of Chlorophyll Content and Potato Crop Yield Using Artificial Intelligence: A Case Study of Salheia, Egypt

Abstract

Abstract Leaf Chlorophyll Concentration (LCC) is a vital biochemical parameter for assessing plant status due to its essential role in physiological activities, photosynthesis, and overall plant health. In order to illustrate the development of potato crops and offer advice for precision agriculture management, research was conducted on non-invasive testing methods for chlorophyll levels and methods for mapping crop yield in potatoes. The objective of this study is to examine the spatial distribution of chlorophyll content and yield of potato crops using Sentinel 2 data, SPAD chlorophyll measurements, and laboratory analyses. Artificial intelligence (AI) using the Random forest (RF) classification method was used to study the spatial distribution of crop type and discriminate the potato crop. The overall accuracy and kappa statistics for the spatial distribution derived from Sentinel 2 satellite imagery for potato crops in the study area were 0.79 and 82.5%, respectively. Stepwise Multilinear regression model (SWMLR) between Spectral vegetation indices (Normalized Difference Vegetation Indexed NDVI, Modified Chlorophyll Absorption Ratio Index (MCARI), Leaf Chlorophyll Index (LCI), derived from spectral vegetation indices (SVI), (SPAD chlorophyll and chemical analysis through potato crop growth stages (S1, S2 and S3) were correlated to estimate chlorophyll content and crop yield map. The model accuracy between vegetation indices and Total chlorophyll showed that models based on VIS and selected spectral bands derived from ASD to predict total chlorophyll(chlt) and SPAD chlorophyll values achieved a high coefficient of determination (R 2 ) at the different growth stages, which were 0.983 and 0.986. The produced map for the potato crop, total chlorophyll derived from Sentinel 2, showed high accuracy at 0.966 and 0.974 based on SPAD, VIS, and selected spectral bands, respectively. The study showed that the estimation and mapping of Chlt and SPAD values of a potato crop under an irrigation system pivot can be done with the help of RS and AI techniques.

Plant phenotyping relevance

Sentinel-2、近接センサー、SPAD、分光データとAI・回帰モデルを用いて、ジャガイモのクロロフィル量と収量を推定・マッピングする技術的評価が研究の中心であり、植物形質の取得・推定方法を扱っている。

Code and data availability

The supplied blocks describe Sentinel-2 imagery, ASD spectroradiometer and SPAD field measurements, and RF/SWMLR modeling, but contain no data availability statement, public dataset deposit, or author code/model release with a URL. No paper-specific public asset is identifiable.

No evidence-backed public reproduction asset is currently recorded.