Coffee Rust Severity Analysis in Agroforestry Systems Using Deep Learning in Peruvian Tropical Ecosystems DOI Creative Commons
Candy Ocaña, Lenin Quiñones Huatangari, Elgar Barboza

и другие.

Agriculture, Год журнала: 2024, Номер 15(1), С. 39 - 39

Опубликована: Дек. 27, 2024

Agroforestry systems can influence the occurrence and abundance of pests diseases because integrating crops with trees or other vegetation create diverse microclimates that may either enhance inhibit their development. This study analyzes severity coffee rust in two agroforestry provinces Jaén San Ignacio department Cajamarca (Peru). research used a quantitative descriptive approach, 319 photographs were collected professional camera during field trips. The segmented, classified analyzed using deep learning MobileNet VGG16 transfer models methods for measuring from SENASA Peru SENASICA Mexico. results reported grade 1 is most prevalent according to methodology (1 5% leaf affected) Mexico (0 2% affected). Moreover, proposed model presented best classification accuracy rate 94% over 50 epochs. demonstrates capacity machine algorithms disease diagnosis, which could be an alternative help experts quantify broadens future low-cost computational tools recognition

Язык: Английский

Multimodal RGB and optical coherence tomography imaging for enhanced machine learning classification of crop diseases and stress phenotyping DOI
Abhishek Banerjee,

Mamta Kumari,

Avinash Kumar

и другие.

Instrumentation Science & Technology, Год журнала: 2025, Номер unknown, С. 1 - 24

Опубликована: Май 6, 2025

Язык: Английский

Процитировано

0
Coffee Rust Severity Analysis in Agroforestry Systems Using Deep Learning in Peruvian Tropical Ecosystems DOI Creative Commons
Candy Ocaña, Lenin Quiñones Huatangari, Elgar Barboza

и другие.

Agriculture, Год журнала: 2024, Номер 15(1), С. 39 - 39

Опубликована: Дек. 27, 2024

Agroforestry systems can influence the occurrence and abundance of pests diseases because integrating crops with trees or other vegetation create diverse microclimates that may either enhance inhibit their development. This study analyzes severity coffee rust in two agroforestry provinces Jaén San Ignacio department Cajamarca (Peru). research used a quantitative descriptive approach, 319 photographs were collected professional camera during field trips. The segmented, classified analyzed using deep learning MobileNet VGG16 transfer models methods for measuring from SENASA Peru SENASICA Mexico. results reported grade 1 is most prevalent according to methodology (1 5% leaf affected) Mexico (0 2% affected). Moreover, proposed model presented best classification accuracy rate 94% over 50 epochs. demonstrates capacity machine algorithms disease diagnosis, which could be an alternative help experts quantify broadens future low-cost computational tools recognition

Язык: Английский

Процитировано

0