Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Evaluating the precise grapevine water stress detection using unmanned aerial vehicles and evapotranspiration-based metrics

  • Burchard-Levine, Vicente
  • Borra-Serrano, Irene
  • Peña Barragán, José Manuel
  • Kustas, William P.
  • Guerra, José G.
  • Dorado, José
  • Mesías-Ruiz, Gustavo A.
  • Herrezuelo, Miguel
  • Mary, Benjamin
  • McKee, Lynn M.
  • Castro, Ana Isabel de
  • Sanchez-Élez, Sara
  • Nieto, Héctor
© The Author(s) 2024. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/., Precise irrigation management requires accurate knowledge of crop water demand to adequately optimize water use efficiency, especially relevant in arid and semi-arid regions. While unoccupied aerial vehicles (UAV) have shown great promise to improve the water management for crops such as vineyards, there still remains large uncertainties to accurately quantify vegetation water requirements, especially through physically-based methods. Notably, thermal remote sensing has been shown to be a promising tool to evaluate water stress at different scales, most commonly through the Crop Water Stress Index (CWSI). This work aimed to evaluate the potential of a UAV payload to estimate evapotranspiration (ET) and alternative ET-based crop water stress indices to better monitor and detect irrigation requirements in vineyards. As a case study, three irrigation treatments within a vineyard were implemented to impose weekly crop coefficient (Kc) of 0.2 (extreme deficit irrigation), 0.4 (typical deficit irrigation) and 0.8 (over-irrigated) of reference ET. Both the original Priestley-Taylor initialized two-source energy balance model (TSEB-PT) and the dual temperature TSEB (TSEB-2T), which takes advantage of high-resolution imagery to discriminate canopy and soil temperatures, were implemented to estimate ET. In a first step, both ET models were evaluated at the footprint level using an eddy covariance (EC) tower, with modelled fluxes comparing well against the EC measurements. Secondly, in-situ physiological measurements at vine level, such as stomatal conductance (gst), leaf (Ψleaf) and stem (Ψstem) water potential, were collected simultaneously to UAV overpasses as plant proxies of water stress. Different variants of the CWSI and alternative metrics that take advantage of the partitioned ET from TSEB, such as Crop Transpiration Stress Index (CTSI) and the Crop Stomatal Stress Index (CSSI), were also evaluated to test their statistical relationship against these in-situ physiological indicators using the Spearman correlation coefficient (ρ). Both TSEB-PT and TSEB-2T CWSI related similarly to in-situ measurements (Ψleaf: ρ ~ 0.4; Ψstem: ρ ~ 0.55). On the other hand, stress indicators using canopy fluxes (i.e. CTSI and CSSI) were much more effective when using TSEB-2 T (Ψleaf: ρ = 0.45; Ψstem: ρ = 0.62) compared to TSEB-PT (Ψleaf: ρ = 0.18; Ψstem: ρ = 0.49), revealing important differences in the ET partitioning between model variants. These results demonstrate the utility of physically-based models to estimate ET and partitioned canopy fluxes, which can enhance the detection of vine water stress and quantitatively assess vine water demand to better manage irrigation practices., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. Spanish Ministry of Science and Innovation and PRIMA EU, PCI2021-121932, PCI2021-121932, PCI2021-121932, PCI2021-121932, PCI2021-121932, PCI2021-121932, Spanish Ministry of Science and Innovation & European Union Next Generation EU/PRTR, FJC2021-047273-I ,FJC2021-047687-1 ,TED2021-129814B-I00, TED2021-129814B-I00, Spanish Ministry of Education and Professional Training, PRE2018-083227., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Weed species classification with UAV imagery and standard CNN models: Assessing the frontiers of training and inference phases

  • Mesías-Ruiz, Gustavo A.
  • Borra-Serrano, Irene
  • Peña Barragán, José Manuel
  • Castro, Ana Isabel de
  • Fernández-Quintanilla, César
  • Dorado, José
12 Pág.-- © 2024 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/)., Accurate weed species identification is crucial for effective site-specific weed management (SSWM), enabling targeted and timely control measures for each weed in crop field. This study advanced the current approach to species-level weed identification during the early growth stage by integrating unmanned aerial vehicles (UAVs) imagery with standard convolutional neural networks (CNNs) models such as VGG16, Resnet152 and Inception-Resnet-v2. For this, a robust dataset was created with 33,467 labels of weeds (Atriplex patula, Chenopodium album, Convolvulus arvensis, Cyperus rotundus, Lolium rigidum, Portulaca oleracea, Salsola kali, Solanum nigrum) and crops (maize, tomato), which was subjected to different training, validation and test scenarios. Model inputs were adjusted in order to align them with the information represented by the UAV images. Initially, models were developed in balanced scenarios, gradually increasing label numbers to assess their performance. Inception-ResNet-v2 achieved over 90% accuracy with 400 labels, while ResNet152 and VGG16 required 600 and 800 labels, respectively, for similar accuracy. In a more complex and realistic scenarios with unbalanced datasets, Inception-ResNet-v2 outperformed, likely due to its deeper architecture and enhanced capability to capture intricate features and patterns within UAV images. The study emphasized the importance of the minority-to-majority species ratio in unbalanced datasets, which affects minority species classification. To prevent misclassification, it is crucial to determine the right number of labels for CNN model training and validation. Weed maps were generated after species classification using the Faster R–CNN algorithm as an object detector. This advancement in methodology facilitates the precise and efficient implementation of SSWM techniques., This work was supported by the Spanish Research State Agency (AEI) through the Project PID2020-113229RB-C41/AEI/10.13039/501100011033. The lead author, G.A. Mesías-Ruiz has been a beneficiary of a FPI fellowship by the Spanish Ministry of Education and Professional Training (PRE2018-083227). The research of I. Borra-Serrano was financed by the grant FJC2021-047687-1 funded by MCIN/AEI/10.13039/501100011033 and European Union NextGenerationEU/PRTR., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Cognitive Computing Advancements: Improving Precision Crop Protection through UAV Imagery for Targeted Weed Monitoring

  • Mesías-Ruiz, Gustavo A.
  • Peña Barragán, José Manuel
  • Castro, Ana Isabel de
  • Borra-Serrano, Irene
  • Dorado, José
20 Pág., Early detection of weeds is crucial to manage weeds effectively, support decision-making and prevent potential crop losses. This research presents an innovative approach to develop a specialized cognitive system for classifying and detecting early-stage weeds at the species level. The primary objective was to create an automated multiclass discrimination system using cognitive computing, regardless of the weed growth stage. Initially, the model was trained and tested on a dataset of 31,002 UAV images, including ten weed species manually identified by experts at the early phenological stages of maize (BBCH14) and tomato (BBCH501). The images were captured at 11 m above ground level. This resulted in a classification accuracy exceeding 99.1% using the vision transformer Swin-T model. Subsequently, generative modeling was employed for data augmentation, resulting in new classification models based on the Swin-T architecture. These models were evaluated on an unbalanced dataset of 36,556 UAV images captured at later phenological stages (maize BBCH17 and tomato BBCH509), achieving a weighted average F1-score ranging from 94.8% to 95.3%. This performance highlights the system’s adaptability to morphological variations and its robustness in diverse crop scenarios, suggesting that the system can be effectively implemented in real agricultural scenarios, significantly reducing the time and resources required for weed identification. The proposed data augmentation technique also proved to be effective in implementing the detection transformer architecture, significantly improving the generalization capability and enabling accurate detection of weeds at different growth stages. The research represents a significant advancement in weed monitoring across phenological stages, with potential applications in precision agriculture and sustainable crop management. Furthermore, the methodology showcases the versatility of the latest generation models for application in other knowledge domains, facilitating time-efficient model development. Future research could investigate the applicability of the model in different geographical regions and with different types of crops, as well as real-time implementation for continuous field monitoring., This research was funded by the SPANISH RESEARCH STATE AGENCY (AEI) through the project PID2020-113229RB-C41/AEI/10.13039/501100011033. The lead author, G.A. Mesías-Ruiz has been a beneficiary of an FPI fellowship by the SPANISH MINISTRY OF EDUCATION AND PROFESSIONAL TRAINING, grant number PRE2018-083227-. The research of I. Borra-Serrano was financed by the grant FJC2021-047687-1 funded by MCIN/AEI/10.13039/501100011033 and EUROPEAN UNION NEXTGENERATIONEU/PRTR., Peer reviewed