Abstract
Water is a crucial element for the growth of watermelon plants, making rapid and non-destructive monitoring of plant water content vital for precision irrigation in watermelon farming. While previous research has demonstrated the sensitivity of short-wave infrared (SWIR) bands to plant water content, their high costs limit widespread application. In contrast, visible and near-infrared (VNIR) spectral instruments offer significant advantages in terms of affordability, compactness, and spectral resolution. However, their potential for predicting the leaf water content (LWC) of watermelon plants has yet to be fully investigated. This study aims to assess the efficacy of hyperspectral reflectance measured with VNIR spectral instruments in estimating the LWC of watermelon plants at various leaf layers. Hyperspectral reflectance data (350−1100 nm) were collected from three leaf layers (upper, middle, and lower) under various drought treatments. Models for estimating LWC were developed using both spectral indices and full wavelength data. The results indicated that the middle leaf layer was the most effective for estimating LWC, and using full wavelength data achieved higher accuracy in LWC estimation. Furthermore, compared to the simple regression model, the AdaBoost-based machine learning model demonstrated superior performance, achieving an R2 of 0.9636 in estimating LWC through five-fold cross-validation, which indicates high predictive accuracy. Ensemble learning significantly outperforms traditional methods, providing a substantial improvement in model accuracy. The findings offer important technical assistance for the spectral monitoring of LWC and precision irrigation in watermelon cultivation.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 5
Claim · model-written summary
The middle leaf layer was the most effective of the three leaf layers for estimating watermelon LWC from hyperspectral reflectance.
- Taxon
- watermelon
Citrullus lanatuse0 - Organ / stage
- middle leaf layere1
- Treatment
- various drought treatmentse2
- Outcome
- most effective for estimating LWCe1
- Comparator
- upper, middle, and lowere2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Water is a crucial element for the growth of watermelon plants”
e1“The results indicated that the middle leaf layer was the most effective for estimating LWC”
e2“Hyperspectral reflectance data (350−1100 nm) were collected from three leaf layers (upper, middle, and lower) under various drought treatments”
Claim · model-written summary
Using full wavelength data gave higher accuracy in watermelon LWC estimation than spectral indices.
- Taxon
- watermelonCitrullus lanatuse0
- Treatment
- full wavelength datae3
- Outcome
- accuracy in LWC estimatione3
- Direction
- highere3
- Comparator
- spectral indicese4
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Water is a crucial element for the growth of watermelon plants”
e3“using full wavelength data achieved higher accuracy in LWC estimation”
e4“Models for estimating LWC were developed using both spectral indices and full wavelength data”
Claim · model-written summary
An AdaBoost-based model outperformed the simple regression model for watermelon LWC, with R2 of 0.9636 under five-fold cross-validation.
- Taxon
- watermelonCitrullus lanatuse0
- Treatment
- AdaBoost-based machine learning modele5
- Outcome
- R2e5
- Direction
- superiore5
- Value
- 0.9636e5
- Qualifier
- five-fold cross-validatione5
- Comparator
- simple regression modele5
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Water is a crucial element for the growth of watermelon plants”
e5“compared to the simple regression model, the AdaBoost-based machine learning model demonstrated superior performance, achieving an R2 of 0.9636 in estimating LWC through five-fold cross-validation”
Claim · model-written summary
Ensemble learning significantly outperformed traditional methods in model accuracy for watermelon LWC estimation.
- Taxon
- watermelonCitrullus lanatuse0
- Treatment
- Ensemble learninge6
- Outcome
- model accuracye6
- Direction
- outperformse6
- Comparator
- traditional methodse6
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Water is a crucial element for the growth of watermelon plants”
e6“Ensemble learning significantly outperforms traditional methods, providing a substantial improvement in model accuracy”
Claim · model-written summary
The findings offer technical assistance for spectral monitoring of LWC and precision irrigation in watermelon cultivation.
- Taxon
- watermelonCitrullus lanatuse7
- Outcome
- spectral monitoring of LWC and precision irrigatione7
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e7“The findings offer important technical assistance for the spectral monitoring of LWC and precision irrigation in watermelon cultivation”