Classification of cotton water stress using convolutional neural networks and UAV-based RGB imagery

Haoyu Niu, Juan Landivar, Nick Duffield

Article ID: 2457
Vol 5, Issue 1, 2024
DOI: https://doi.org/10.54517/ama.v5i1.2457
VIEWS - 344 (Abstract)

Abstract

Embracing smart irrigation management techniques empowers growers to irrigate with greater efficiency, thereby promoting sustainable agricultural production. In this context, growers often rely on crop evapotranspiration (ETc) as a key factor in making informed irrigation decisions, underscoring the significance of accurately determining and spatially mapping crop water status. Technological progress, exemplified by the emergence of unmanned aerial vehicles (UAVs), has brought about a revolutionary shift in agricultural monitoring. UAV platforms can capture high-resolution images with centimeter-level spatial accuracy and offer higher temporal coverage compared to satellite imagery. Considering these advancements, this study introduces a robust method for classifying water stress in cotton using a compact UAV platform and convolutional neural networks (CNN). The experiment was conducted at the USDA-ARS Cropping Systems Research Laboratory (CSRL) in Lubbock, Texas, where the cotton field was divided into 12 drip zones. The study included three replications to evaluate four irrigation treatments: “rainfed”, “full irrigation”, “percent deficit of full irrigation”, and “time delay of full irrigation”. The results demonstrated that the CNN model successfully classified the cotton water stress using the UAV-based RGB image, achieving an overall best prediction accuracy of approximately 91%. By segmenting the original cotton images into separate canopy and soil areas using morphological image processing methods, the authors also isolated and analyzed the individual contributions of these components to cotton water stress. Additionally, a random forest classifier revealed the relative importance of different image features in the classification process through feature importance analysis. These findings highlighted the state-of-the-art performance of the proposed system in cotton water stress classification and provided valuable insights into the key image features contributing to accurate classification. The authors concluded that integrating UAV-based RGB imagery and CNN models had great potential for assessing water stress in cotton.


Keywords

cotton; irrigation; water stress; UAV; RGB; evapotranspiration; convolutional neural networks; random forest

Full Text:

PDF



References

1. Johnson J, Kiawu J, Macdonald S, et al. The world and United States cotton outlook. Available online: http://ageconsearch.umn.edu (accessed on 2 December 2023).

2. Adhikari P, Ale S, Bordovsky JP, et al. Simulating future climate change impacts on seed cotton yield in the Texas High Plains using the CSM-CROPGRO-Cotton model. Agricultural Water Management. 2016, 164: 317-330. doi: 10.1016/j.agwat.2015.10.011

3. Ale S, Himanshu SK, Mauget SA, et al. Simulated Dryland Cotton Yield Response to Selected Scenario Factors Associated with Soil Health. Frontiers in Sustainable Food Systems. 2021, 4. doi: 10.3389/fsufs.2020.617509

4. Bordovsky JP, Mustian JT, Ritchie GL, Lewis KL. Cotton irrigation timing with variable seasonal irrigation capacities in the Texas South Plains. Applied Engineering in Agriculture. 2015, 31(6): 883-897. doi: 10.13031/aea.31.10953

5. Allen RG, Pereira LS. Crop evapotranspiration (guidelines for computing crop water requirements). Available online: https://www.fao.org/3/x0490e/x0490e00.htm (accessed on 2 December 2023).

6. Hatfield JL, Dold C. Water-Use Efficiency: Advances and Challenges in a Changing Climate. Frontiers in Plant Science. 2019, 10. doi: 10.3389/fpls.2019.00103

7. Kaplan S, Myint SW, Fan C, et al. Quantifying Outdoor Water Consumption of Urban Land Use/Land Cover: Sensitivity to Drought. Environmental Management. 2014, 53(4): 855-864. doi: 10.1007/s00267-014-0245-7

8. Niu H, Hollenbeck D, Zhao T, et al. Evapotranspiration Estimation with Small UAVs in Precision Agriculture. Sensors. 2020, 20(22): 6427. doi: 10.3390/s20226427

9. Gowda PH, Chavez JL, Colaizzi PD, et al. ET mapping for agricultural water management: present status and challenges. Irrigation Science. 2007, 26(3): 223-237. doi: 10.1007/s00271-007-0088-6

10. Niu H, Chen Y. Towards Tree-Level Evapotranspiration Estimation with Small UAVs in Precision Agriculture. Springer International Publishing; 2022. doi: 10.1007/978-3-031-14937-5

11. Zhao WL, Qiu GY, Jiu YX, et al. Uncertainties caused by resistances in evapotranspiration estimation using high-density eddy covariance measurements. Journal of Hydrometeorology. 2020, 21(6): 1349–1365. doi: 10.1175/JHM-D-19-0191.1

12. Niu H, Zhao T, Wang D, et al. A UAV resolution and waveband aware path planning for onion irrigation treatments inference. In: Proceedings of the 2019 International Conference on Unmanned Aircraft Systems (ICUAS); 11–14 June 2019; Atlanta, GA, USA. pp. 808–812. doi: 10.1109/icuas.2019.8798188

13. Zhao T, Wang D, Niu H, et al. Onion irrigation treatment inference using a low-cost hyperspectral scanner. In: Proceedings of the Multispectral, Hyperspectral, and Ultraspectral Remote Sensing Technology, Techniques and Applications VII; 24–26 September 2018; Honolulu, Hawaii, United States. doi: 10.1117/12.2325500

14. Zhao T, Chen Y, Ray A, et al. Quantifying almond water stress using unmanned aerial vehicles (UAVs): Correlation of stem water potential and higher order moments of non-normalized canopy distribution. In: Proceedings of the 13th ASME/IEEE International Conference on Mechatronic and Embedded Systems and Applications; 6–9 August 2017; Cleveland, Ohio, USA. doi: 10.1115/detc2017-68246

15. Zhang L, Zhang H, Niu Y, et al. Mapping Maize Water Stress Based on UAV Multispectral Remote Sensing. Remote Sensing. 2019, 11(6): 605. doi: 10.3390/rs11060605

16. Khanal S, Fulton J, Shearer S. An overview of current and potential applications of thermal remote sensing in precision agriculture. Computers and Electronics in Agriculture. 2017, 139: 22-32. doi: 10.1016/j.compag.2017.05.001

17. Viers J, Niu H, Zhao T, et al. A detailed study on accuracy of uncooled thermal cameras by exploring the data collection workflow. In: Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping III. SPIE; 2018. doi: 10.1117/12.2305217

18. Hoffmann H, Nieto H, Jensen R, et al. Estimating evaporation with thermal UAV data and two-source energy balance models. Hydrology and Earth System Sciences. 2016, 20(2): 697-713. doi: 10.5194/hess-20-697-2016

19. Ribeiro-Gomes K, Hernández-López D, Ortega J, et al. Uncooled Thermal Camera Calibration and Optimization of the Photogrammetry Process for UAV Applications in Agriculture. Sensors. 2017, 17(10): 2173. doi: 10.3390/s17102173

20. Niu H, Zhao T, Wei J, et al. Reliable tree-level evapotranspiration estimation of pomegranate trees using lysimeter and UAV multispectral imagery. In: Proceedings of the 2021 IEEE Conference on Technologies for Sustainability (SusTech); 22–24 April 2021; Irvine, CA, USA. pp. 1–6. doi: 10.1109/sustech51236.2021.9467413

21. Bian J, Zhang Z, Chen J, et al. Simplified Evaluation of Cotton Water Stress Using High Resolution Unmanned Aerial Vehicle Thermal Imagery. Remote Sensing. 2019, 11(3): 267. doi: 10.3390/rs11030267

22. Zhang L, Niu Y, Zhang H, et al. Maize Canopy Temperature Extracted from UAV Thermal and RGB Imagery and Its Application in Water Stress Monitoring. Frontiers in Plant Science. 2019, 10. doi: 10.3389/fpls.2019.01270

23. Aversano L, Bernardi ML, Cimitile M. Water stress classification using Convolutional Deep Neural Networks. JUCS - Journal of Universal Computer Science. 2022, 28(3): 311-328. doi: 10.3897/jucs.80733

24. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015, 521(7553): 436-444. doi: 10.1038/nature14539

25. Khaki S, Wang L, Archontoulis SV. A CNN-RNN Framework for Crop Yield Prediction. Frontiers in Plant Science. 2020, 10. doi: 10.3389/fpls.2019.01750

26. Chandel NS, Chakraborty SK, Rajwade YA, et al. Identifying crop water stress using deep learning models. Neural Computing and Applications. 2020, 33(10): 5353-5367. doi: 10.1007/s00521-020-05325-4

27. Li R, Jia X, Hu M, et al. An Effective Data Augmentation Strategy for CNN-Based Pest Localization and Recognition in the Field. IEEE Access. 2019, 7: 160274-160283. doi: 10.1109/access.2019.2949852

28. Yang W, Nigon T, Hao Z, et al. Estimation of corn yield based on hyperspectral imagery and convolutional neural network. Computers and Electronics in Agriculture. 2021, 184: 106092. doi: 10.1016/j.compag.2021.106092

29. Gonzalez RC, Woods RE, Eddins SL. Digital Image Processing Using MATLAB, 3rd ed. Gatesmark Publishing; 2020.

30. Szeliski R. Computer Vision. Springer International Publishing; 2022. doi: 10.1007/978-3-030-34372-9

31. Billmeyer FW. Color Science: Concepts and Methods, Quantitative Data and Formulae, 2nd ed., by Gunter Wyszecki and W. S. Stiles, John Wiley and Sons, New York, 1982, 950 pp. Price: $75.00. Color Research & Application. 1983, 8(4): 262-263. doi: 10.1002/col.5080080421

32. Otsu N. A Threshold Selection Method from Gray-Level Histograms. IEEE Transactions on Systems, Man, and Cybernetics. 1979, 9(1): 62-66. doi: 10.1109/tsmc.1979.4310076

33. Ashapure A, Jung J, Chang A, et al. A Comparative Study of RGB and Multispectral Sensor-Based Cotton Canopy Cover Modelling Using Multi-Temporal UAS Data. Remote Sensing. 2019, 11(23): 2757. doi: 10.3390/rs11232757

34. Trout TJ, Johnson LF, Gartung J. Remote Sensing of Canopy Cover in Horticultural Crops. HortScience. 2008, 43(2): 333-337. doi: 10.21273/hortsci.43.2.333

35. Ashapure A, Jung J, Chang A, et al. Developing a machine learning based cotton yield estimation framework using multi-temporal UAS data. ISPRS Journal of Photogrammetry and Remote Sensing. 2020, 169: 180-194. doi: 10.1016/j.isprsjprs.2020.09.015

36. Patrignani A, Ochsner TE. Canopeo: A Powerful New Tool for Measuring Fractional Green Canopy Cover. Agronomy Journal. 2015, 107(6): 2312-2320. doi: 10.2134/agronj15.0150

37. Meyer GE, Neto JC. Verification of color vegetation indices for automated crop imaging applications. Computers and Electronics in Agriculture. 2008, 63(2): 282-293. doi: 10.1016/j.compag.2008.03.009

38. Paruelo JM, Lauenroth WK, Roset PA. Estimating Aboveground Plant Biomass Using a Photographic Technique. Journal of Range Management. 2000, 53(2): 190. doi: 10.2307/4003281

39. Pal M. Random Forest classifier for remote sensing classification. International Journal of Remote Sensing. 2005, 26(1): 217-222. doi: 10.1080/01431160412331269698

40. Larrinaga A, Brotons L. Greenness Indices from a Low-Cost UAV Imagery as Tools for Monitoring Post-Fire Forest Recovery. Drones. 2019, 3(1): 6. doi: 10.3390/drones3010006

41. Ortega-Farias S, Espinoza-Meza S, López-Olivari R, et al. Effects of different irrigation levels on plant water status, yield, fruit quality, and water productivity in a drip-irrigated blueberry orchard under Mediterranean conditions. Agricultural Water Management. 2021, 249: 106805. doi: 10.1016/j.agwat.2021.106805

42. Zhang D, Liu Y, Li Y, et al. Reducing the Excessive Evaporative Demand Improved the Water-use Efficiency of Greenhouse Cucumber by Regulating the Trade-off between Irrigation Demand and Plant Productivity. HortScience. 2018, 53(12): 1784-1790. doi: 10.21273/hortsci13129-18

43. Tarara JM, Perez Peña JE. Moderate Water Stress from Regulated Deficit Irrigation Decreases Transpiration Similarly to Net Carbon Exchange in Grapevine Canopies. Journal of the American Society for Horticultural Science. 2015, 140(5): 413-426. doi: 10.21273/jashs.140.5.413

44. Morales-Santos A, Nolz R. Assessment of canopy temperature-based water stress indices for irrigated and rainfed soybeans under subhumid conditions. Agricultural Water Management. 2023, 279: 108214. doi: 10.1016/j.agwat.2023.108214

45. Yuan Y, Wu L, Zhang X. Gini-Impurity Index Analysis. IEEE Transactions on Information Forensics and Security. 2021, 16: 3154-3169. doi: 10.1109/tifs.2021.3076932

46. Ballester C, Brinkhoff J, Quayle WC, et al. Monitoring the Effects of Water Stress in Cotton using the Green Red Vegetation Index and Red Edge Ratio. Remote Sensing. 2019, 11(7): 873. doi: 10.3390/rs11070873

47. Tong A, He Y. Estimating and mapping chlorophyll content for a heterogeneous grassland: Comparing prediction power of a suite of vegetation indices across scales between years. ISPRS Journal of Photogrammetry and Remote Sensing. 2017, 126: 146-167. doi: 10.1016/j.isprsjprs.2017.02.010

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 Haoyu Niu, Juan Landivar, Nick Duffield

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.


This site is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).