Machine Learning-Based Spectral Library for Crop Classification and Status Monitoring
Abstract
:1. Introduction
2. Materials and Methods
2.1. Data Acquisition for Construction of a Crop Spectral Library
2.1.1. Experiment 1: Spectral Data Collection for Crop Classification
2.1.2. Experiment 2: Spectral Data Collection for Crop Growth Monitoring
Experiment on Tea Plant Growth Vigor Monitoring
Experiment on Rice Growth Stage Monitoring
2.1.3. Measurement of Crop Canopy Hyperspectral Data
2.2. Extraction and Analysis of Spectral Features
2.2.1. Extraction of Spectral Features
2.2.2. Sensitivity Analysis of Spectral Features
2.3. Classification Models and Accuracy Assessment
3. Results and Discussion
3.1. Sensitive Features for Vegetation Classification and Growth Status Monitoring
3.2. Spectral Library-Based Crop Classification
3.3. Spectral Library-Based Crop Growing Status Monitoring
4. Conclusions
Author Contributions
Acknowledgments
Conflicts of Interest
Appendix A
ID | Plant Common Name | Species Name | ID | Plant Common Name | Species Name |
---|---|---|---|---|---|
1 | Citrus | Citrus reticulata Blanco | 45 | Phaseolus Vulgaris | Radermachera sinica (Hance) Hemsl. |
2 | Peach | Amygdalus persica Linn. | 46 | Larix Principis-Rupprechtii | Larix gmelinii var. principis-rupprechtii (Mayr) Pilg. |
3 | Ginkgo | Ginkgo biloba L. | 47 | Banana | Musa basjoo Siebold |
4 | Loquat | Eriobotrya japonica (Thunb.) Lindl. | 48 | Calycanthaceae | Calycanthaecae |
5 | Shaddock | Citrus maxima (Burm.) Osbeck | 49 | Podocarpus | Podocarpus macrophyllus D. Don |
6 | Cowpea | Vigna unguiculate (Linn.) Walp. | 50 | Bougainvillea | Bougainvillea spectabilis Willd. |
7 | Soybean | Glycine max (L.) Merr. | 51 | Japanese Five-Needle Pine | Pinus parviflora Sieb. et Zucc. |
8 | Sweet Potato | Ipomoea batatas (L.) Poir. | 52 | Evergreen | Rohdea japonica (Thunb.) Roth |
9 | Peanut | Arachis hypogaea Linn. | 53 | Platycladus Orientalis | Platycladus orientalis (Linn.) Franco |
10 | Amaranth | Amaranthus tricolor Linn. | 54 | Ligustrum Lucidum | Ligustrum lucidum Ait. |
11 | Eggplant | Solanum melongena Linn. | 55 | Phyllostachys Crenata | Bambusa multiplex’ Fernleaf’ R. A. Young |
12 | Sesame | Sesamum indicum Linn. | 56 | Cycas | Cycas revoluta Thunb |
13 | Youxian Camellia Oleifera | Camellia yuhsienensis Hu | 57 | Elm | Ulmus pumila L. |
14 | Rice | Oryza sativa | 58 | Pseudolarix | Pseudolarix amabilis (Nelson) Rehd. |
15 | Wheat | Triticum aestivum Linn. | 59 | Forsythia | Duranta erecta L. |
16 | Tea | Camellia sinensis (L.) O. Ktze. | 60 | Dragon Cypress | Juniperus chinensis’ Kaizuka’ |
17 | Buxus Microphylla | Buxus sinica var. parvifolia M. Cheng | 61 | Sunflower | Helianthus annuus Linn. |
18 | Herb Trinity | Viola tricolor Linn. | 62 | Zelkova Schneideriana | Zelkova schneideriana Hand. -Mazz. |
19 | Elaeocarpus Decipiens | Elaeocarpus decipiens Hemsl. | 63 | Bambusa Multiplex | Bambusa multiplex ’Alphonso-Karrii’ R. A. Young |
20 | Handkerchief Tree | Davidia involucrate Baill. | 64 | Yulan Magnolia | Yulania denudate (Desr.) D. L. Fu |
21 | Camphor Tree | Cinnamomum camphora (L.) J.Presl. | 65 | Wisteria | Wisteria sinensis (Sims) Sweet |
22 | Michelia Maudiae | Michelia maudiae Dunn. | 66 | Rhus Succedanea | Toxicodendron succedaneum (Linn.) O. Kuntze |
23 | Chinese Pagoda Tree | Sophora japonica’ Pendula’ Hort. | 67 | Hibiscus Mutabilis | Hibiscus mutabilis Linn. |
24 | Plum Blossom | Armeniaca mume Sieb. | 68 | Awn | Miscanthus sinensis Anderss. |
25 | Red Wooden | Loropetalum chinense var. rubrum Yieh | 69 | Ilex Crenata | Ilex crenata Thunb. |
26 | Magnolia | Magnolia grandiflora L. | 70 | Willow | Salix babylonica Linn. |
27 | Japanese Maple | Acer palmatum Thunb. | 71 | Rudbeckia Laciniata | Rudbeckia laciniate Linn. |
28 | Cedar | Cedrus deodara (Roxb.) G. Don | 72 | Eleusine Indica | Eleusine indica (Linn.) Gaertn. |
29 | White Oak | Quercus fabri Hance | 73 | Soapberry | Sapindus Saponaria L. |
30 | Pampasgrass | Cortaderia selloana (Schult.) Aschers. et Graebn. | 74 | Reed Bamboo | Arundo donax L. |
31 | Red Maple | Acer palmatum’ Atropurpureum’ | 75 | Banana Shrub | Michelia figo (Lour.) Spreng. |
32 | Sweet-Scented Osmanthus | Osmanthus fragrans Lour. | 76 | Sedum Sinensis | Sedum sarmentosum Bunge |
33 | Hackberry | Celtis sinensis Pers. | 77 | Rhododendron | Rhododendron simsii Planch. |
34 | Illicium Lanceolatum | Illicium lanceolatum A. C. Sm. | 78 | Lotus | Nelumbo nucifera Gaertn. |
35 | Bambusa Vulgaris Schrad | Phyllostachys aureosulcata’ Spectabilis’ | 79 | Pyracantha | Pyracantha fortuneana (Maxim.) Li |
36 | Ilex Cornuta | Ilex cornuta Lindl. et Paxt. | 80 | Hasaki | Euonymus japonicus’ Aureo-marginatus’ |
37 | Canna | Canna indica L. | 81 | Ligustrum Lucidum | Ligustrum vicaryi Rehder |
38 | Petunia Hybrida | Petunia hybrida Vilmorin | 82 | Paspalum | Paspalum thunbergii Kunth ex Steud. |
39 | Liquidambar Formosana | Liquidambar formosana Hance | 83 | Torenia Fournieri | Torenia fournieri Linden. ex Fourn. |
40 | Palm | Trachycarpus fortune (Hook.) H. Wendl. | 84 | Graperoot | Mahonia fortune (Lindl.) Fedde |
41 | Dalbergia | Dalbergia hupeana Hance | 85 | Moor Besom | Photinia serratifolia (Desf.) Kalkman |
42 | Camellia Puniceiflora Chang | Camellia puniceiflora H. T. Chang | 86 | Pink | Dianthus chinensis Linn. |
43 | Carbungi | Typha angustifolia L. | 87 | Marigold | Tagetes erecta Linn. |
44 | Phyllostachys Heterocycla | Phyllostachys edulis’ Heterocycla’ |
References
- Campos-Taberner, M.; García-Haro, F.J.; Confalonieri, R.; Martínez, B.; Busetto, L. Multitemporal Monitoring of Plant Area Index in the Valencia Rice District with PocketLAI. Remote Sens. Environ. 2016, 8, 202. [Google Scholar] [CrossRef]
- Du, M.; Noguchi, N. Monitoring of Wheat Growth Status and Mapping of Wheat Yield’s Within-Field Spatial Variations Using Color Images Acquired from UAV-camera System. Remote Sens. Environ. 2017, 9, 289. [Google Scholar] [CrossRef]
- Jin, X.; Kumar, L.; Li, Z.; Xu, X.; Yang, G.; Wang, J. Estimation of Winter Wheat Biomass and Yield by Combining the AquaCrop Model and Field Hyperspectral Data. Remote Sens. Environ. 2016, 8, 972. [Google Scholar] [CrossRef]
- Pu, R. Hyperspectral Remote Sensing: Fundamentals and Practices; CRC Press: Boca Raton, USA, 2017. [Google Scholar]
- Adão, T.; Hruška, J.; Pádua, L.; Bessa, J.; Peres, E.; Morais, R.; Sousa, J. Hyperspectral Imaging: A Review on UAV-Based Sensors, Data Processing and Applications for Agriculture and Forestry. Remote Sens. 2017, 9, 1110. [Google Scholar] [CrossRef]
- Pu, R.; Liu, D. Segmented canonical discriminant analysis of hyperspectral data for identifying 13 urban tree species. Int. J. Remote Sens. 2011, 32, 2207–2226. [Google Scholar] [CrossRef]
- Underwood, E.C.; Ustin, S.L.; Ramirez, C.M. A Comparison of Spatial and Spectral Image Resolution for Mapping Invasive Plants in Coastal California. J. Environ. Manag. 2007, 39, 63–83. [Google Scholar] [CrossRef] [PubMed]
- Underwood, E.; Ustin, S.; Dipietro, D. Mapping nonnative plants using hyperspectral imagery. Remote Sens. Environ. 2003, 86, 150–161. [Google Scholar] [CrossRef]
- Jin, H.; Sun, Y.H.; Wang, M.Y.; Zhang, D.D.; Sada, R.; Li, M.C. Juvenile tree classification based on hyperspectral image acquired from an unmanned aerial vehicle. Int. J. Remote Sens. 2017, 38, 2273–2295. [Google Scholar]
- Yuan, H.; Yang, G.; Li, C.; Wang, Y.; Liu, J.; Yu, H.; Feng, H.; Xu, B.; Zhao, X.; Yang, X. Retrieving Soybean Leaf Area Index from Unmanned Aerial Vehicle Hyperspectral Remote Sensing: Analysis of RF, ANN, and SVM Regression Models. Remote Sens. 2017, 9, 309. [Google Scholar] [CrossRef]
- Backhaus, A.; Bollenbeck, F.; Seiffert, U. Robust classification of the nutrition state in crop plants by hyperspectral imaging and artificial neural networks. In Proceedings of the 3rd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), Lisbon, Portugal, 6–9 June 2011. [Google Scholar]
- Senthilnath, J.; Omkar, S.N.; Mani, V.; Karnwal, N.; Shreyas, P.B. Crop Stage Classification of Hyperspectral Data Using Unsupervised Techniques. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2013, 6, 861–866. [Google Scholar] [CrossRef]
- Duarte-Carvajalino, J.; Alzate, D.; Ramirez, A.; Santa, J.; Fajardo-Rojas, A.; Soto-Suárez, M. Evaluating Late Blight Severity in Potato Crops Using Unmanned Aerial Vehicles and Machine Learning Algorithms. Remote Sens. 2018, 10, 1513. [Google Scholar] [CrossRef]
- Baldridge, A.M.; Hook, S.J.; Grove, C.I.; Rivera, G. The ASTER spectral library version 2.0. Remote Sens. Environ. 2009, 113, 711–715. [Google Scholar] [CrossRef]
- Nidamanuri, R.R.; Zbell, B. Transferring spectral libraries of canopy reflectance for crop classification using hyperspectral remote sensing data. Biosyst. Eng. 2011, 110, 231–246. [Google Scholar] [CrossRef]
- Baret, F.; Guyot, G. Potentials and limits of vegetation indices for LAI and APAR assessment. Remote Sens. Environ. 1991, 35, 161–173. [Google Scholar] [CrossRef]
- Zarco-Tejada, P.; Berjón, A.; Lopez-Lozano, R.; Miller, J.; Martín, P.; Cachorro, V.; González, M.R.; de Frutos, A. Assessing vineyard condition with hyperspectral indices: Leaf and canopy reflectance simulation in a row-structured discontinuous canopy. Remote Sens. Environ. 2005, 99, 271–287. [Google Scholar] [CrossRef]
- Qi, J.; Chehbouni, A.; Huete, A.R.; Kerr, Y.H.; Sorooshian, S.S. A modified soil adjusted vegetation index. Remote Sens. Environ. 1994, 48, 119–126. [Google Scholar] [CrossRef]
- Rouse, J.W.; Haas, R.H.; Schell, J.A.; Deering, D.W. Monitoring Vegetation Systems in the Great Plains with ERTS. In NASA. Goddard Space Flight Center; Texas A&M Univniversity: College Station, TX, USA, 1973. [Google Scholar]
- Koppe, W.; Fei, L.; Gnyp, M.L.; Miao, Y.; Bareth, G. Evaluating Multispectral and Hyperspectral Satellite Remote Sensing Data for Estimating Winter Wheat Growth Parameters at Regional Scale in the North China Plain. Photogramm Fernerkun 2010, 2010, 167–178. [Google Scholar] [CrossRef] [Green Version]
- Blackburn, G.A. Quantifying Chlorophylls and Caroteniods at Leaf and Canopy Scales: An Evaluation of Some Hyperspectral Approaches. Remote Sens. Environ. 1998, 66, 273–285. [Google Scholar] [CrossRef]
- Schlerf, M.; Atzberger, C.; Hill, J. Remote sensing of forest biophysical variables using HyMap imaging spectrometer data. Remote Sens. Environ. 2005, 95, 177–194. [Google Scholar] [CrossRef] [Green Version]
- Delalieux, S.; Somers, B.; Hereijgers, S.; Verstraeten, W.W.; Keulemans, W.; Coppin, P. A near-infrared narrow-waveband ratio to determine Leaf Area Index in orchards. Remote Sens. Environ. 2008, 112, 3762–3772. [Google Scholar] [CrossRef]
- Vincini, M.; Frazzi, E.; D Alessio, P. Angular dependence of maize and sugar beet VIs from directional CHRIS/PROBA data. In Proceedings of the 4th ESA CHRIS PROBA Workshop, ESRIN, Frascati, Italy, 19–21 September 2006. [Google Scholar]
- Gamon, J.A.; Peñuelas, J.; Field, C.B. A narrow-waveband spectral index that tracks diurnal changes in photosynthetic efficiency. Remote Sens. Environ. 1992, 41, 35–44. [Google Scholar] [CrossRef]
- Gitelson, A.A.; Merzlyak, M.N.; Chivkunova, O.B. Optical properties and nondestructive estimation of anthocyanin content in plant leaves. J. Photochem. Photobiol. B-Biol. 2001, 74, 38–45. [Google Scholar] [CrossRef]
- Gitelson, A.A.; Merzlyak, M.N. Signature Analysis of Leaf Reflectance Spectra: Algorithm Development for Remote Sensing of Chlorophyll. J. Plant. Physiol. 1996, 148, 494–500. [Google Scholar] [CrossRef]
- Gitelson, A.A. Remote estimation of canopy chlorophyll content in crops. Geophys. Res. Lett. 2005, 32, L08403. [Google Scholar] [CrossRef]
- Gitelson, A.A.; Kaufman, Y.J.; Stark, R.; Rundquist, D. Novel algorithms for remote estimation of vegetation fraction. Remote Sens. Environ. 2002, 80, 76–87. [Google Scholar] [CrossRef] [Green Version]
- Datt, B. A New Reflectance Index for Remote Sensing of Chlorophyll Content in Higher Plants: Tests using Eucalyptus Leaves. J. Plant. Physiol. 1999, 154, 30–36. [Google Scholar] [CrossRef]
- Daughtry, C.S.T.; Walthall, C.L.; Kim, M.S.; Colstoun, E.B.D.; McMurtrey III, J.E. Estimating Corn Leaf Chlorophyll Concentration from Leaf and Canopy Reflectance. Remote Sens. Environ. 2000, 74, 229–239. [Google Scholar] [CrossRef]
- Peñuelas, J.; Gamon, J.A.; Fredeen, A.L.; Merino, J.; Field, C.B. Reflectance indices associated with physiological changes in nitrogen- and water-limited sunflower leaves. Remote Sens. Environ. 1994, 48, 135–146. [Google Scholar] [CrossRef]
- Nagler, P.L.; Daughtry, C.S.T.; Goward, S.N. Plant Litter and Soil Reflectance. Remote Sens. Environ. 2000, 71, 207–215. [Google Scholar] [CrossRef]
- Serrano, L.; Peñuelas, J.; Ustin, S.L. Remote sensing of nitrogen and lignin in Mediterranean vegetation from AVIRIS data: Decomposing biochemical from structural signals. Remote Sens. Environ. 2002, 81, 355–364. [Google Scholar] [CrossRef]
- Galvao, L.S.; Formaggio, A.R.; Tisot, D.A. Discrimination of sugarcane varieties in Southeastern Brazil with EO-1 Hyperion data. Remote Sens. Environ. 2005, 94, 523–534. [Google Scholar] [CrossRef]
- Hardisky, M.; Klemas, V.; Smart, R.M. The influence of soil salinity, growth form, and leaf moisture on the spectral radiance of Spartina Alterniflora canopies. Photogramm. Eng. Remote Sens. 1983, 49, 77–84. [Google Scholar]
- Gao, B. NDWI–A Normalized Difference Water Index for Remote Sensing of Vegetation Liquid Water from Space. Remote Sens. Environ. 1996, 58, 257–266. [Google Scholar] [CrossRef]
- Pu, R.; Ge, S.; Kelly, N.M.; Gong, P. Spectral absorption features as indicators of water status in coast live oak (Quercus agrifolia) leaves. Int. J. Remote Sens. 2003, 24, 1799–1810. [Google Scholar] [CrossRef]
- Fensholt, R.; Sandholt, I. Derivation of a shortwave infrared water stress index from MODIS near–and shortwave infrared data in a semiarid environment. Remote Sens. Environ. 2003, 87, 111–121. [Google Scholar] [CrossRef]
- Peñuelas, J.; Pinol, J.; Ogaya, R.; Filella, I. Estimation of Plant Water Concentration by the Reflectance Water Index WI (R900/R970). Int. J. Remote Sens. 1997, 18, 2869–2875. [Google Scholar] [CrossRef]
- Ball, G.H.; Hall, D.J. ISODATA, A Novel Method of Data Analysis and Pattern Classification; Stanford Research Institute: Menlo Park, CA, USA, 1965. [Google Scholar]
- Swain, P.H.; Davis, S.M. Remote Sensing: The Quantitative Approach. IEEE Trans. Pattern Anal. Mach. Intell. 1981, 6, 713–714. [Google Scholar] [CrossRef]
- Hastie, T.; Tibshirani, R.; Friedman, J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction; Springer: New York, NY, USA, 2009; pp. 459–483. [Google Scholar]
- Pal, M. Random forest classifier for remote sensing classification. Int. J. Remote Sens. 2005, 26, 217–222. [Google Scholar] [CrossRef]
- Belgiu, M.; Drăguţ, L. Random forest in remote sensing: A review of applications and future directions. Isprs-J. Photogramm. Remote Sens. 2016, 114, 24–31. [Google Scholar] [CrossRef]
- Chi, M.; Feng, R.; Bruzzone, L. Classification of hyperspectral remote-sensing data with primal SVM for small-sized training dataset problem. Adv. Space Res. 2008, 41, 1793–1799. [Google Scholar] [CrossRef]
- Congalton, R.G.; Mead, R.A. A quantitative method to test for consistency and correctness in photo-interpretation. Photogramm. Eng. Remote Sens. 1983, 49, 69–74. [Google Scholar]
- Curran, P.J. Remote sensing of foliar chemistry. Remote Sens. Environ. 1989, 30, 271–278. [Google Scholar] [CrossRef]
- Wolpert, D.H. The Lack of A Priori Distinctions Between Learning Algorithms. Neural Comput. 1996, 8, 1341–1390. [Google Scholar] [CrossRef]
Monitoring Contents | Machine Learning Methods | Accuracy | Reference |
---|---|---|---|
Urban tree species (13 species) | Segmented canonical discriminant analysis (CDA), segmented principal component analysis (PCA), segmented stepwise discriminate analysis (SDA), and segmented maximum likelihood classifier (MLC) | OAA:76–96% | Pu and Liu [6] |
Invasive species (Carpobrotus edulis, Cortaderia jubata, Eucalyptus globulus) | PCA and minimum noise fraction (MNF) | OAA:37–75% | Underwood et al. [7] |
Nonnative plant species (Carpobrotus edulis, jubata grass, and Cortaderia jubata) | MLC | OAA:55–97% | Underwood et al. [8] |
Juvenile tree species (9 species) | Maximum likelihood (ML) | OAA:68–96% | Huang et al. [9] |
Soybean growth | Random forest (RF), artificial neural network (ANN), support vector machine (SVM) | R2:0.674–0.749 | Yuan et al. [10] |
Tobacco leaf nitrogen levels | SVM, supervised relevance neural gas (SRNG), generalized relevance learning vector quantization (GRLVQ), radial basis function (RBF) | OAA:2.2–99.8% | Backhaus et al. [11] |
Wheat growth stages | iterative self-organizing data analysis (ISODATA), artificial immune system (AIS), hierarchical artificial immune system (HAIS), niche stratified artificial immune system (NHAIS) | OAA:59.5–81.5% | Senthilnath et al. [12] |
Potato disease (Late Blight) | Multi-layer perceptron (MLP), convolutional neural network (CNN), support vector regression (SVR), random forest (RF) | R2:0.44–0.74 | Duarte-Carvajalino [13] |
Plants’ Name | Status | Time | Location | Sample Size |
---|---|---|---|---|
Tea tree | Growth (Three levels) | August 2017 | Hangzhou, China tea laboratory base | 14 × 10 (poor growth) + 16 × 10 (medium growth) + 16 × 10 (good growth) = 460 |
Rice | Growing stage (Five stages) | August 2018 | Fu yang, Hangzhou, China National Rice Research Institute | 5 (stages) × 12 (plots) × 5 = 300 |
Feature Type | Position | Band Range (nm) | Feature |
---|---|---|---|
First derivative feature | Blue edge | 490–540 | Maximum differential value (BMV) |
Position of the maximum differential value (BPMV) | |||
Sum of differential values (BSV) | |||
Yellow edge | 540–620 | Maximum differential value (YMV) | |
Position of the maximum differential value (YPMV) | |||
Sum of differential values (YSV) | |||
Red edge | 660–780 | Maximum differential value (RMV) | |
Position of the maximum differential value (RPMV) | |||
Sum of differential values (RSV) | |||
Continuous removal feature | Near infrared | 530–770 | Depth |
Width | |||
Area |
Spectral Index | Characteristics & Functions | Definition | Reference |
---|---|---|---|
Structure (LAI, crown closure, Green biomass, Species, etc.) | |||
ATSAVI, Adjusted Transformed Soil-Adjusted VI | Less affected by soil background and better for estimating homogeneous canopy | a × (R800 − a × R670 − b)/ [(a × R800 + R670 − a × b + X × (1 + a²)], where X = 0.08, a = 1.22, and b = 0.03 | Baret and Guyot 1991 [16] |
GI, Greenness Index | Estimate biochemical constituents and LAI at leaf and canopy levels | R554/R677 | Zarco-Tejada et al. 2005 [17] |
MSAVI, Improved Soil Adjusted Vegetation Index | A more sensitive indicator of vegetation amount than SAVI at canopy level | 0.5 × [2R800 + 1 − ((2R800 + 1) × 2 − 8(R800 − R670)) × 1/2] | Qi et al. 1994 [18] |
NBNDVI, Narrow-Band Normalized Difference Vegetation Index | Responds to change in the amount of green biomass and more efficiently in vegetation with low to moderate density | (R850 − R680)/(R850 + R680) | Rouse et al. 1973 [19] |
NRI, Normalized Ratio Index | A sensitive indicator of biomass, N concentration and height of crop (wheat) | (R874 − R1225)/(R874 + R1225) | Koppe et al. 2010 [20] |
PSND, Pigment-Specific Normalized Difference | Estimate LAI and Cars at leaf or canopy level | (R800 − R470)/(R800 + R470) | Blackburn.1998 [21] |
PVIhyp, Hyperspectral Perpendicular VI | More efficiently quantify the low amount of vegetation by minimizing soil background influence on vegetation spectrum | (R1148 − aR807 − b)/(1 + a²) × 1/2, a = 1.17, b = 3.37 | Schlerf et al. 2005 [22] |
sLAIDI, Normalization or Standard of the LAIDI | Sensitive to LAI variation at canopy level with a saturation point >8 | S × (R1050 − R1250)/(R1050 + R1250), where S = 5 | Delalieux et al. 2008 [23] |
SPVI, Spectral polygon vegetation index | Estimate LAI and canopy Chls | 0.4 × [3.7 × (R800 − R670) − 1.2 × |R530 − R670|] | Vincini et al. 2006 [24] |
Pigments (Chls, Cars, and Anths) | |||
PRI, Photochemical /Physiological Reflectance Index | Estimate carotenoid pigment contents in foliage | (R531 − R570)/(R531 + R570) | Gamon et al. 1992 [25] |
ARI, Anthocyanin Reflectance Index | Estimate Anths content from reflectance changes in the green region at leaf level | (R550) − 1 − (R700) − 1 | Gitelson et al. 2001 [26] |
BRI, Blue Red Pigment Index | Estimate Chls and Cars content at leaf and canopy levels | R450/R690 | Zarco-Tejada et al. 2005 [17] |
CI, Chlorophyll Index | Estimate Chls content in broadleaf tree leaves | (R750 − R705)/(R750 + R705); R750/[(R700 + R710) − 1] | Gitelson and Merzlyak 1996 [27]; Gitelson et al. 2005 [28] |
CRI, Carotenoid Reflectance Index | Sufficient to estimate total Cars content in plant leaves | CRI550 = (R510) − 1 − (R550) − 1; CRI700 = (R510) − 1 − (R700) − 1 | Gitelson et al. 2002 [29] |
LCI, Leaf Chlorophyll Index | Estimate Chl content in higher plants, sensitive to variation in reflectance caused by Chl absorption | (R850 − R710)/(R850 + R680) | Datt. 1999 [30] |
MCARI, Modified Chlorophyll Absorption in Reflectance Index | Respond to Chl variation and estimate Chl absorption | [(R701 − R671) − 0.2(R701 − R549)] (R701/R671) | Daughtry et al. 2000 [31] |
NPCI, Normalized Pigment Chlorophyll ratio Index | Assess Cars/Chl ratio at leaf level | (R680 − R430)/(R680 + R430) | Peñuelas et al. 1994 [32] |
Other Biochemicals | |||
CAI, Cellulose Absorption Index | Cellulose & lignin absorption features, discriminates plant litter from soils | 0.5 × (R2020 + R2220) − R2100 | Nagler et al. 2000 [33] |
NDLI, Normalized Difference Lignin Index | Quantify variation of canopy lignin concentration in native shrub vegetation | [log(1/R1754) − log(1/R1680)]/log(1/R1754) + log(1/R1680)] | Serrano et al. 2002 [34] |
NDNI, Normalized Difference Nitrogen Index | Quantify variation of canopy N concentration in native shrub vegetation | [log(1/R1510) − log(1/R1680)]/ [log(1/R1510) + log(1/R1680)] | Serrano et al. 2002 [34] |
Water | |||
LWVI-1, Leaf Water VI 1 | Estimate leaf water content, an NDWI variant | (R1094 − R893)/(R1094 + R893) | Galvão et al. 2005 [35] |
NDII, Normalized Difference Infrared Index | Detect variation of leaf water content | (R819 − R1600)/(R819 + R1600) | Hardinsky et al. 1983 [36] |
NDWI, ND Water Index | Improving the accuracy in retrieving the vegetation water content at both leaf and canopy levels | (R860 − R1240)/(R860 + R1240) | Gao 1996 [37] |
RATIO975, 3-band ratio at 975 nm | Estimate relative water content <60% at leaf level | 2 × R960-990/(R920-940 + R1090-1110) | Pu et al. 2003 [38] |
SIWSI, Shortwave Infrared Water Stress Index | Estimate leaf or canopy water stress, especially in the semiarid environment | (R860 − R1640)/(R860 + R1640) | Fensholt and Sandholt 2003 [39] |
WI, Water Index | Quantify relative water content at leaf level | R900/R970 | Peñuelas et al. 1997 [40] |
Application Scene | Selected Spectral Features | |||
---|---|---|---|---|
Bands (nm) | First Derivative Feature | Continuous Removal Feature | VIs | |
Crop classification | 396,417,527, 676,699,1333, 1457,484,1445 | None | Width | sLAIDI, NRI, GI, NDII, PRI, BRI, WI |
Growth monitoring of tea trees | 673,733,761, 823,1454,1517, 2024 | None | Depth | LWVI-1, WI, sLAIDI, SIWSI, PVIhyp, NDII, NBNDVI, NRI, NDWI |
Growth stage monitoring of rice | 431,534,721, 749,1026,333, 1497,1599,660, 2023 | BSV, YSV, BMV | None | PRI, CRI700, ARI, NPCI, RATIO975, BRI, LWVI-1 |
Application Scene | Feature Selected | RF | GA-SVM | KNN | |||
---|---|---|---|---|---|---|---|
OAA | KAPPA | OAA | KAPPA | OAA | KAPPA | ||
Crop classification | Spectral bands | 0.82 | 0.81 | 0.90 | 0.90 | 0.65 | 0.62 |
Spectral features | 0.91 | 0.90 | 0.94 | 0.93 | 0.82 | 0.81 | |
Band + Features | 0.93 | 0.92 | 0.94 | 0.93 | 0.83 | 0.82 | |
Growth monitoring of tea trees | Spectral bands | 0.80 | 0.71 | 0.89 | 0.84 | 0.74 | 0.62 |
Spectral features | 0.86 | 0.80 | 0.88 | 0.81 | 0.79 | 0.68 | |
Band + Features | 0.86 | 0.79 | 0.98 | 0.97 | 0.77 | 0.65 | |
Growth stage monitoring of rice | Spectral bands | 0.76 | 0.70 | 0.88 | 0.85 | 0.71 | 0.64 |
Spectral features | 0.87 | 0.83 | 0.92 | 0.90 | 0.79 | 0.74 | |
Band + Features | 0.85 | 0.81 | 0.92 | 0.90 | 0.77 | 0.71 |
© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhang, J.; He, Y.; Yuan, L.; Liu, P.; Zhou, X.; Huang, Y. Machine Learning-Based Spectral Library for Crop Classification and Status Monitoring. Agronomy 2019, 9, 496. https://doi.org/10.3390/agronomy9090496
Zhang J, He Y, Yuan L, Liu P, Zhou X, Huang Y. Machine Learning-Based Spectral Library for Crop Classification and Status Monitoring. Agronomy. 2019; 9(9):496. https://doi.org/10.3390/agronomy9090496
Chicago/Turabian StyleZhang, Jingcheng, Yuhang He, Lin Yuan, Peng Liu, Xianfeng Zhou, and Yanbo Huang. 2019. "Machine Learning-Based Spectral Library for Crop Classification and Status Monitoring" Agronomy 9, no. 9: 496. https://doi.org/10.3390/agronomy9090496