Vase-Life Monitoring System for Cut Flowers Using Deep Learning and Multiple Cameras DOI Creative Commons

Ji Yeong Ham,

Yong-Tae Kim, Suong Tuyet Thi Ha

et al.

Plants, Journal Year: 2025, Volume and Issue: 14(7), P. 1076 - 1076

Published: April 1, 2025

Here, we developed a vase-life monitoring system (VMS) to automatically and accurately assess the post-harvest quality vase life (VL) of cut roses. The VMS integrates camera imaging with YOLOv8 (You Only Look Once version 8) deep learning algorithm continuously monitor major physiological parameters including flower opening, fresh weight, water uptake, gray mold disease incidence. Our results showed that can measure main factors roses by obtaining precise consistent data. values measured for physiology closely correlated those observation (OBS). Additionally, achieved high performance in model an object detection accuracy 90%. mAP0.5 supported evaluating VL Regression analysis revealed strong correlation between VL, VMS, OBS. incorporating microscope detected early stages development. These show plant is highly effective method using could also be applied breeding process, which requires rapid measurements important characteristics species, such as resistance, develop superior cultivars.

Language: Английский

Crop Yield Prediction Using Machine Learning: An Extensive and Systematic Literature Review DOI Creative Commons

Sarowar Morshed Shawon,

Falguny Barua Ema,

Asura Khanom Mahi

et al.

Smart Agricultural Technology, Journal Year: 2024, Volume and Issue: unknown, P. 100718 - 100718

Published: Dec. 1, 2024

Language: Английский

Citations

4
Bridging the gap between hyperspectral imaging and crop breeding: soybean yield prediction and lodging classification with prototype contrastive learning DOI
Guangyao Sun, Zhang Yong, Lei Wang

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 230, P. 109859 - 109859

Published: Jan. 5, 2025

Language: Английский

Citations

0
UAV Remote Sensing Technology for Wheat Growth Monitoring in Precision Agriculture: Comparison of Data Quality and Growth Parameter Inversion DOI Creative Commons
Jikai Liu, Weiqiang Wang, Jun Li

et al.

Agronomy, Journal Year: 2025, Volume and Issue: 15(1), P. 159 - 159

Published: Jan. 10, 2025

The quality of the image data and potential to invert crop growth parameters are essential for effectively using unmanned aerial vehicle (UAV)-based sensor systems in precision agriculture (PA). However, existing research falls short providing a comprehensive examination inversion parameters, there is still ambiguity regarding how affects potential. Therefore, this study explored application RGB multispectral (MS) images acquired from three lightweight UAV platforms realm PA: DJI Mavic 2 Pro (M2P), Phantom 4 Multispectral (P4M), 3 (M3M). reliability pixel-scale was evaluated based on assessment metrics, winter wheat above-ground biomass (AGB), plant nitrogen content (PNC) soil analysis development (SPAD), were inverted machine learning models multi-source features at plot scale. results indicated that M3M outperformed M2P, while MS marginally superior P4M. Nevertheless, these advantages did not improve accuracy Spectral (SFs) derived P4M-based demonstrated significant AGB (R2 = 0.86, rRMSE 27.47%), SFs M2P-based camera exhibited best performance SPAD 0.60, 7.67%). Additionally, combining spectral textural yielded highest PNC 0.82, 14.62%). This clarified prevalent mounted PA their influence parameter potential, offering guidance selecting appropriate sensors monitoring key parameters.

Language: Английский

Citations

0
UAV-based rice aboveground biomass estimation using a random forest model with multi-organ feature selection DOI Creative Commons
Jing Shi, Kaili Yang,

Ningge Yuan

et al.

European Journal of Agronomy, Journal Year: 2025, Volume and Issue: 164, P. 127529 - 127529

Published: Feb. 10, 2025

Language: Английский

Citations

0
Identification of maize kernel varieties based on interpretable ensemble algorithms DOI Creative Commons

Chunguang Bi,

Xinhua Bi,

Jinjing Liu

et al.

Frontiers in Plant Science, Journal Year: 2025, Volume and Issue: 16

Published: Feb. 12, 2025

Introduction Maize kernel variety identification is crucial for reducing storage losses and ensuring food security. Traditional single models show limitations in processing large-scale multimodal data. Methods This study constructed an interpretable ensemble learning model maize seed through improved differential evolutionary algorithm data fusion. Morphological hyperspectral of samples were extracted preprocessed, three methods used to screen features, respectively. The base learner the Stacking integration was selected using diversity performance indices, with parameters optimized a evolution incorporating multiple mutation strategies dynamic adjustment factors recombination rates. Shapley Additive exPlanation applied learning. Results HDE-Stacking achieved 97.78% accuracy. spectral bands at 784 nm, 910 732 962 666 nm showed positive impacts on results. Discussion research provides scientific basis efficient different corn varieties, enhancing accuracy traceability germplasm resource management. findings have significant practical value agricultural production, improving quality management efficiency contributing security assurance.

Language: Английский

Citations

0
A cascaded autoencoder unmixing network for Hyperspectral anomaly detection DOI Creative Commons
Kun Li, Yingqian Wang, Qiang Ling

et al.

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2025, Volume and Issue: 136, P. 104405 - 104405

Published: Feb. 1, 2025

Language: Английский

Citations

0
Hyperspectral Band Selection for Crop Identification and Mapping of Agriculture DOI Creative Commons
Yulei Tan,

Jian-Ying Gu,

Laijun Lu

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(4), P. 663 - 663

Published: Feb. 15, 2025

Different crops, as well the same crop at different growth stages, display distinct spectral and spatial characteristics in hyperspectral images (HSIs) due to variations their chemical composition structural features. However, narrow bandwidth closely spaced channels of HSIs result significant data redundancy, posing challenges identification classification. Therefore, dimensionality reduction is crucial. Band selection a widely used method for reducing has been extensively applied research on mapping. In this paper, superpixel-based affinity propagation (CS-AP) band proposed mapping agriculture using HSIs. The approach begins by gathering superpixels; then, criterion developed analyzing superpixels. Finally, bands are determined through an efficient clustering approach, AP. Two typical agricultural sets, Salinas Valley set Indian Pines set, selected validation, each containing 16 classes, respectively. experimental results show that CS-AP achieves accuracy 92.4% 88.6% set. When compared all bands, two unsupervised techniques, three semi-supervised outperforms others with improvement 3.1% 4.3% Indicate superior selecting fewer greater capability other methods. This research’s demonstrate potential precision agriculture, offering more cost-effective timely solution large-scale monitoring future.

Language: Английский

Citations

0
Effects of broad-leaved grass inhibitors and nitrogen fertilizer on seed production Elymus nutans in alpine meadow of the Qinghai-Tibet Plateau DOI Creative Commons
Xin Lu, Juan Qi, Junhu Su

et al.

Frontiers in Plant Science, Journal Year: 2025, Volume and Issue: 16

Published: Feb. 17, 2025

Introduction The alpine meadows of the Tibetan Plateau play a crucial role in grassland ecosystem. However, due to rapid growth and strong competitiveness broad-leaved grasses, nutritional resources living space available for Gramineae species are severely restricted this region. Broad-leaved grasses noxious weeds have evolved into dominant population, limiting production meadows. A shortage premium seeds limits ecosystem restoration efforts. Elymus nutans is regarded as pioneer plant restoring degraded dominated by developing cultivated region, demand native E. increasing. Methods Therefore, study investigated effect combinations four levels grass inhibitor (0, 0.9, 1.5, 2.1 kg·hm -2 ) crossed with nitrogen fertilizer 75, 150, 225 on seed Gannan meadow Qinghai-Tibet Plateau. Results We observed that significantly ( p < 0.05) influenced fertile tillers (FT), spikelets per tiller (SFT), spikelet (SS) panicle length (PL), but not florets (FS) = 0.145). Nitrogen FT, FS, SS, PL 0.001), SFT 0.068). interaction had no significant any these yield components > 0.05). Both all indicators increasing their values dose-dependent manner. Moreover, proved except actual 0.05), demonstrating synergistic effects. maximum thousand weight (4.66 g) (365 were at highest doss fertilizer, which 1.85-fold 2.94-fold control, respectively. Furthermore, positive correlations among components. Pathway analysis showed FT made direct contributions yield. Discussion This approach (using inhibitors fertilizer) effectively reduced competition from increased proportion community composition, thus alleviating ecological restoration.

Language: Английский

Citations

0
Prediction of sugar beet yield and quality parameters using stacked-LSTM model with pre-harvest UAV time series data and meteorological factors DOI Creative Commons
Qing Wang,

Ke Shao,

Zhibo Cai

et al.

Artificial Intelligence in Agriculture, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

Citations

0
Retrieving the chlorophyll content of individual apple trees by reducing canopy shadow impact via a 3D radiative transfer model and UAV multispectral imagery DOI Creative Commons
Chengjian Zhang, Zhibo Chen, Riqiang Chen

et al.

Plant Phenomics, Journal Year: 2025, Volume and Issue: unknown, P. 100015 - 100015

Published: March 1, 2025

Language: Английский

Citations

0