Image-based leaf SPAD value and chlorophyll measurement using a mobile phone: enabling accessible and sustainable crop management
Anderson, J.; Boonyaves, K.; Okamoto, H.; Karaket, N.; Chuekong, W.; Garvie, M.; Chabang, N.; Osorio, D.; Supaibulwatana, K.
Show abstract
This study evaluates a practical, low-cost solution for image-based leaf SPAD (Soil and Plant Analysis Development) value and chlorophyll content monitoring using a mobile phone. We compare laboratory assay and SPAD-502+ measurements with image-based estimates from a mobile phone app (PhotoFolia). Performance is tested for four commercial rice varieties grown in Thailand. Results show that the image-based method can predict SPAD values within {+/-} 1.2 units Mean Absolute Error (MAE) and chlorophyll concentrations within 7.2% Mean Absolute Percentage Error (MAPE) of laboratory results. Achieving a SPAD value error close to the industry standard of {+/-}1 unit and a relative error of less than 10% in chlorophyll concentration estimation (compared to a laboratory method) demonstrates that an image-based approach using standard mobile phones can serve as an accessible, low-cost tool for on-farm chlorophyll monitoring, without the need for specialised equipment.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Accelerating leaf area measurement using a volumetric approach 96%
- Developmental Normalization of Phenomics Data Generated by High Throughput Plant Phenotyping Systems 95%
- Monitoring of drought stress and transpiration rate using proximal thermal and hyperspectral imaging in an indoor automated plant phenotyping platform 95%
Similar papers in this journal
- UV reflectance in crop remote sensing: Assessing the current state of knowledge and extending research with strawberry cultivars. 96%
- Suitability of resampled multispectral datasets for mapping flowering plants in the Kenyan savannah 94%
- Multi-trait random regression models increase genomic prediction accuracy for a temporal physiological trait derived from high-throughput phenotyping 93%
Similar papers in this journal
- Low-cost, handheld near-infrared spectroscopy for root dry matter content prediction in cassava 95%
- Robustness of high-throughput prediction of leaf ecophysiological traits using near infra-red spectroscopy and poro-fluorometry 95%
- Quantifying Leaf Symptoms of Sorghum Charcoal Rot in Images of Field-Grown Plants 9 Using Deep Neural Networks 94%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.