Deep Learning Sensor Fusion in Plant Water Stress Assessment: A Comprehensive Review
Source abstract
Abstract
Water stress is one of the major challenges to food security, causing a significant economic loss for the nation as well for growers. Accurate assessment of water stress will enhance agricultural productivity through optimization of plant water usage, maximizing plant breeding strategies, and preventing forest wildfire for better ecosystem management. Recent advancements in sensor technologies have enabled high-throughput, non-contact, and cost-efficient plant water stress assessment through intelligence system modeling. The advanced deep learning sensor fusion technique has been reported to improve the performance of the machine learning application for processing the collected sensory data. This paper extensively reviews the state-of-the-art methods for plant water stress assessment that utilized the deep learning sensor fusion approach in their application, together with future prospects and challenges of the application domain. Notably, 37 deep learning solutions fell under six main areas, namely soil moisture estimation, soil water modelling, evapotranspiration estimation, evapotranspiration forecasting, plant water status estimation and plant water stress identification. Basically, there are eight deep learning solutions compiled for the 3D-dimensional data and plant varieties challenge, including unbalanced data that occurred due to isohydric plants, and the effect of variations that occur within the same species but cultivated from different locations.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI · Remote Sensing in Agriculture · Greenhouse Technology and Climate Control
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Malaysia-Japan International Institute of Technology, Universiti Teknologi Malaysia, Jalan Sultan Yahya Petra, Kuala Lumpur 54100, Malaysia
Centre for Artificial Intelligence and Robotics, Universiti Teknologi Malaysia, Jalan Sultan Yahya Petra, Kuala Lumpur 54100, Malaysia
Department of Cell and Molecular Biology, Faculty of Biotechnology and Biomolecular Sciences, Universiti Putra Malaysia, Selangor 43400, Malaysia
Funding
Ministry of Higher Education, Malaysia · Universiti Teknologi Malaysia
References (100+)
Show source-provided references
1. Osakabe, Y., Osakabe, K., Shinozaki, K., and Tran, L.-S. (2014). Response of plants to water stress. Front. Plant Sci., 5.10.3389/fpls.2014.00086 ↗
2. Effect of irrigation scheduling on potato crop parameters under water stressed conditions10.1016/S0378-3774(02)00110-5 ↗
3. Lisar, S.Y., Motafakkerazad, R., Hossain, M.M., and Rahman, I.M. (2012). Water stress in plants: Causes, effects and responses. Water Stress, InTech.10.5772/39363 ↗
4. Win-win: Improved irrigation management saves water and increases yield for robusta coffee farms in Vietnam10.1016/j.agwat.2020.106350 ↗
5. Assessment of the water status of mandarin and peach canopies using visible multispectral imagery10.1016/j.biosystemseng.2008.04.001 ↗
6. Regulated deficit irrigation for crop production under drought stress. A review10.1007/s13593-015-0338-6 ↗
7. Monitoring water stress and fruit quality in an orange orchard under regulated deficit irrigation using narrow-band structural and physiological remote sensing indices10.1016/j.isprsjprs.2012.05.003 ↗
8. Combining NDVI and surface temperature for the estimation of live fuel moisture content in forest fire danger rating10.1016/j.rse.2004.01.019 ↗
9. Predicting water stress induced by Thaumastocoris peregrinus infestations in plantation forests using field spectroscopy and neural networks10.1080/14498596.2013.821679 ↗
10. New phenotyping methods for screening wheat and barley for beneficial responses to water deficit10.1093/jxb/erq199 ↗
11. Evaluating the utility of remotely sensed soil moisture retrievals for operational agricultural drought monitoring10.1109/JSTARS.2009.2037163 ↗
12. Using satellite-based soil moisture to detect and monitor spatiotemporal traces of agricultural drought over Bundelkhand region of India10.1080/15481603.2017.1286725 ↗
13. Ecophysiological modeling of grapevine water stress in burgundy terroirs by a machine-learning approach10.3389/fpls.2016.00796 ↗
14. Recent advances in crop water stress detection10.1016/j.compag.2017.07.026 ↗
15. Water Stress and Plant Growth 110.2134/agronj1963.00021962005500010013x ↗
16. Sensing technologies for precision specialty crop production10.1016/j.compag.2010.08.005 ↗
17. Gerhards, M., Schlerf, M., Mallick, K., and Udelhoven, T. (2019). Challenges and Future Perspectives of Multi-/Hyperspectral Thermal Infrared Remote Sensing for Crop Water-Stress Detection: A Review. Remote Sens., 11.10.3390/rs11101240 ↗
18. Alvino, A., and Marino, S. (2017). Remote sensing for irrigation of horticultural crops. Horticulturae, 3.10.3390/horticulturae3020040 ↗
19. Remote sensing and machine learning for crop water stress determination in various crops: A critical review10.1007/s11119-020-09711-9 ↗
20. Liakos, K.G., Busato, P., Moshou, D., Pearson, S., and Bochtis, D. (2018). Machine Learning in Agriculture: A Review. Sensors, 18.10.3390/s18082674 ↗
21. Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review10.1016/j.compag.2018.05.012 ↗
22. Deep learning in remote sensing applications: A meta-analysis and review10.1016/j.isprsjprs.2019.04.015 ↗
23. Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data10.1109/LGRS.2017.2681128 ↗
24. Deep learning in environmental remote sensing: Achievements and challenges10.1016/j.rse.2020.111716 ↗
25. Computer vision-based phenotyping for improvement of plant productivity: A machine learning perspective
26. Deep learning in agriculture: A survey10.1016/j.compag.2018.02.016 ↗
27. Gao, Z., Luo, Z., Zhang, W., Lv, Z., and Xu, Y. (2020). Deep Learning Application in Plant Stress Imaging: A Review. AgriEngineering, 2.10.3390/agriengineering2030029 ↗
28. Deep learning for plant stress phenotyping: Trends and future perspectives10.1016/j.tplants.2018.07.004 ↗
29. Use of Deep Learning Techniques for Identification of Plant Leaf Stresses: A Review
30. Reducing the dimensionality of data with neural networks10.1126/science.1127647 ↗
31. Deep learning: Methods and applications10.1561/2000000039 ↗
32. Deep learning in neural networks: An overview10.1016/j.neunet.2014.09.003 ↗
33. An agricultural monitoring system based on wireless sensor and depth learning algorithm10.3991/ijoe.v13i12.7885 ↗
34. Study and comparison of color models for automatic image analysis in irrigation management applications10.1016/j.agwat.2014.08.010 ↗
35. Neural-intelligent water drops algorithm to select relevant textural features for developing precision irrigation system using machine vision10.1016/j.compag.2011.05.005 ↗
36. Hyperspectral image analysis for water stress detection of apple trees10.1016/j.compag.2011.04.008 ↗
37. Gutiérrez, S., Diago, M.P., Fernández-Novales, J., and Tardaguila, J. (2018). Vineyard water status assessment using on-the-go thermal imaging and machine learning. PLoS ONE, 13.10.1371/journal.pone.0192037 ↗
38. Boxel, D.V. (2017). Hands-On Deep Learning with TensorFlow, Packt Publishing.
39. Ketkar, N., and Santana, E. (2017). Deep Learning with Python, Springer.10.1007/978-1-4842-2766-4 ↗
40. Bisong, E. (2019). Google Colaboratory. Building Machine Learning and Deep Learning Models on Google Cloud Platform: A Comprehensive Guide for Beginners, Apress.10.1007/978-1-4842-4470-8 ↗
41. Performance analysis of google colaboratory as a tool for accelerating deep learning applications10.1109/ACCESS.2018.2874767 ↗
42. Deep plant phenomics: A deep learning platform for complex plant phenotyping tasks10.3389/fpls.2017.01190 ↗
43. An explainable deep machine vision framework for plant stress phenotyping10.1073/pnas.1716999115 ↗
44. A versatile phenotyping system and analytics platform reveals diverse temporal responses to water availability in Setaria10.1016/j.molp.2015.06.005 ↗
45. Feldman, M.J., Paul, R.E., Banan, D., Barrett, J.F., Sebastian, J., Yee, M.-C., Jiang, H., Lipka, A.E., Brutnell, T.P., and Dinneny, J.R. (2017). Time dependent genetic analysis links field and controlled environment phenotypes in the model C4 grass Setaria. PLoS Genet., 13.10.1371/journal.pgen.1006841 ↗
46. A fast learning algorithm for deep belief nets10.1162/neco.2006.18.7.1527 ↗
47. A review of the use of convolutional neural networks in agriculture10.1017/S0021859618000436 ↗
48. Imagenet classification with deep convolutional neural networks
49. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
50. Tran, D., Bourdev, L., Fergus, R., Torresani, L., and Paluri, M. (2015, January 7–13). Learning spatiotemporal features with 3d convolutional networks. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.510 ↗
51. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
52. Backpropagation through time: What it does and how to do it10.1109/5.58337 ↗
53. Mikolov, T., Kombrink, S., Burget, L., Černocký, J., and Khudanpur, S. (2011, January 22–27). Extensions of recurrent neural network language model. Proceedings of the 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic.10.1109/ICASSP.2011.5947611 ↗
54. Graves, A., Mohamed, A.-R., and Hinton, G. (2013, January 26–31). Speech recognition with deep recurrent neural networks. Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada.10.1109/ICASSP.2013.6638947 ↗
55. A step towards new irrigation scheduling strategies using plant-based measurements and mathematical modelling10.1007/s00271-008-0111-6 ↗
56. Evaluation of machine learning methods to predict soil moisture constants with different combinations of soil input data for calcareous soils in a semi arid area10.1016/j.agwat.2020.106121 ↗
57. Sobayo, R., Wu, H., Ray, R., and Qian, L. (2018, January 8–10). Integration of Convolutional Neural Network and Thermal Images into Soil Moisture Estimation. Proceedings of the 2018 1st International Conference on Data Intelligence and Security (ICDIS), South Padre Island, TX, USA.10.1109/ICDIS.2018.00041 ↗
58. Tseng, D., Wang, D., Chen, C., Miller, L., Song, W., Viers, J., Vougioukas, S., Carpin, S., Ojea, J.A., and Goldberg, K. (2018, January 20–24). Towards Automating Precision Irrigation: Deep Learning to Infer Local Soil Moisture Conditions from Synthetic Aerial Agricultural Images. Proceedings of the 2018 IEEE 14th International Conference on Automation Science and Engineering (CASE), Munich, Germany.10.1109/COASE.2018.8560431 ↗
59. Zhang, D., Zhang, W., Huang, W., Hong, Z., and Meng, L. (2017). Upscaling of surface soil moisture using a deep learning model with VIIRS RDR. ISPRS Int. J. Geo-Inf., 6.10.3390/ijgi6050130 ↗
60. Estimation of soil moisture using deep learning based on satellite data: A case study of South Korea10.1080/15481603.2018.1489943 ↗
61. Extracting Soil Moisture from Fengyun-3D Medium Resolution Spectral Imager-II Imagery by Using a Deep Belief Network10.1007/s13351-020-9191-x ↗
62. Ge, L., Hang, R., Liu, Y., and Liu, Q. (2018). Comparing the performance of neural network and deep convolutional neural network in estimating soil moisture from satellite observations. Remote Sens., 10.10.3390/rs10091327 ↗
63. Adeyemi, T., Grove, I., Peets, S., Domun, Y., and Norton, T. (2018). Dynamic Neural Network Modelling of Soil Moisture Content for Predictive Irrigation Scheduling. Sensors, 18.10.3390/s18103408 ↗
64. Modeling spatio-temporal distribution of soil moisture by deep learning-based cellular automata model10.1007/s40333-016-0049-0 ↗
65. Cai, Y., Zheng, W., Zhang, X., Zhangzhong, L., and Xue, X. (2019). Research on soil moisture prediction model based on deep learning. PLoS ONE, 14.10.1371/journal.pone.0214508 ↗
66. A hybrid CNN-GRU model for predicting soil moisture in maize root zone10.1016/j.agwat.2020.106649 ↗
67. A Deep Learning Approach for Multi-Depth Soil Water Content Prediction in Summer Maize Growth Period10.1109/ACCESS.2020.3034984 ↗
68. Prolongation of SMAP to spatiotemporally seamless coverage of continental US using a deep learning neural network10.1002/2017GL075619 ↗
69. Near-real-time forecast of satellite-based soil moisture using long short-term memory with an adaptive data integration kernel10.1175/JHM-D-19-0169.1 ↗
70. Assessment of evapotranspiration and soil moisture content across different scales of observation10.3390/s8010070 ↗
71. Comparison of soybean evapotranspirations measured by weighing lysimeter and Bowen ratio-energy balance methods
72. Allen, R.G. (1998). Crop Evapotranspiration—Guidelines for Computing Crop Water Requirements-FAO Irrigation and Drainage Paper 56, FAO.
73. Evaluation of thermal remote sensing indices to estimate crop evapotranspiration coefficients10.1016/j.agwat.2016.07.007 ↗
74. Reference evapotranspiration estimation and modeling of the Punjab Northern India using deep learning10.1016/j.compag.2018.11.031 ↗
75. New approach to estimate daily reference evapotranspiration based on hourly temperature and relative humidity using machine learning and deep learning10.1016/j.agwat.2020.106113 ↗
76. Afzaal, H., Farooque, A.A., Abbas, F., Acharya, B., and Esau, T. (2020). Computation of evapotranspiration with artificial intelligence for precision water resource management. Appl. Sci., 10.10.3390/app10051621 ↗
77. Estimating daily reference evapotranspiration based on limited meteorological data using deep learning and classical machine learning methods10.1016/j.jhydrol.2020.125286 ↗
78. Bai, S., Kolter, J.Z., and Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv.
79. Niu, H., Hollenbeck, D., Zhao, T., Wang, D., and Chen, Y. (2020). Evapotranspiration Estimation with Small UAVs in Precision Agriculture. Sensors, 20.10.3390/s20226427 ↗
80. Cui, Y., Ma, S., Yao, Z., Chen, X., Luo, Z., Fan, W., and Hong, Y. (2020). Developing a Gap-Filling Algorithm Using DNN for the Ts-VI Triangle Model to Obtain Temporally Continuous Daily Actual Evapotranspiration in an Arid Area of China. Remote Sens., 12.10.3390/rs12071121 ↗
81. García-Pedrero, A.M., Gonzalo-Martín, C., Lillo-Saavedra, M.F., Rodriguéz-Esparragón, D., and Menasalvas, E. (2017). Convolutional neural networks for estimating spatially distributed evapotranspiration. Image and Signal Processing for Remote Sensing XXIII, International Society for Optics and Photonics.10.1117/12.2278321 ↗
82. Prediction Model of Transpiration Rate of Strawberry in Closed Cultivation Based on DBN-LSSVM Algorithm10.1016/j.ifacol.2018.08.171 ↗
83. Estimation of daily maize transpiration using support vector machines, extreme gradient boosting, artificial and deep neural networks models10.1016/j.agwat.2020.106547 ↗
84. Multi-step ahead forecasting of daily reference evapotranspiration using deep learning10.1016/j.compag.2020.105728 ↗
85. Reference evapotranspiration time series forecasting with ensemble of convolutional neural networks10.1016/j.compag.2020.105700 ↗
86. Forecast of short-term daily reference evapotranspiration under limited meteorological variables using a hybrid bi-directional long short-term memory model (Bi-LSTM)10.1016/j.agwat.2020.106386 ↗
87. Temporal convolution-network-based models for modeling maize evapotranspiration under mulched drip irrigation10.1016/j.compag.2019.105206 ↗
88. Modeling long-term dynamics of crop evapotranspiration using deep learning in a semi-arid environment10.1016/j.agwat.2020.106334 ↗
89. Determination of water deficits in plant tissues
90. Retrieving vegetation canopy water content from hyperspectral thermal measurements10.1016/j.agrformet.2017.08.020 ↗
91. Determination of a suitable indicator of tomato water content based on stem diameter variation10.1016/j.scienta.2016.11.053 ↗
92. Meng, Z., Duan, A., Chen, D., Dassanayake, K.B., Wang, X., Liu, Z., Liu, H., and Gao, S. (2017). Suitable indicators using stem diameter variation-derived indices to monitor the water status of greenhouse tomato plants. PLoS ONE, 12.10.1371/journal.pone.0171423 ↗
93. Irrigation scheduling: Advantages and pitfalls of plant-based methods10.1093/jxb/erh213 ↗
94. Vineyard water status estimation using multispectral imagery from an UAV platform and machine learning algorithms for irrigation scheduling management10.1016/j.compag.2018.02.013 ↗
95. Loggenberg, K., Strever, A., Greyling, B., and Poona, N. (2018). Modelling water stress in a shiraz vineyard using hyperspectral imaging and machine learning. Remote Sens., 10.10.3390/rs10020202 ↗
96. Poblete, T., Ortega-Farías, S., Moreno, M., and Bardeen, M. (2017). Artificial neural network to predict vine water status spatial variability using multispectral information obtained from an unmanned aerial vehicle (UAV). Sensors, 17.10.3390/s17112488 ↗
97. Instantaneous and non-destructive relative water content estimation from deep learning applied to resonant ultrasonic spectra of plant leaves
98. Multi-modal sliding window-based support vector regression for predicting plant water stress10.1016/j.knosys.2017.07.028 ↗
99. Multimodal neural network with clustering-based drop for estimating plant water stress10.1016/j.compag.2019.105118 ↗
100. Water content estimation in vegetation with MODIS reflectance data and model inversion methods10.1016/S0034-4257(02)00197-9 ↗