Detection of Weed Species in Soybean Using Multispectral Digital Images1

The objective of this research was to assess the accuracy of remote sensing for detecting weed species in soybean based on two primary criteria: the presence or absence of weeds and the identification of individual weed species. Treatments included weeds (giant foxtail and velvetleaf) grown in monoculture or interseeded with soybean, bare ground, and weed-free soybean. Aerial multispectral digital images were collected at or near soybean canopy closure from two field sites in 2001. Weedy pixels (1.3 m2) were separated from weed-free soybean and bare ground with no more than 11% error, depending on the site. However, the classification of weed species varied between sites. At one site, velvetleaf and giant foxtail were classified with no more than 17% error, when monoculture and interseeded plots were combined. However, classification errors were as high as 39% for velvetleaf and 17% for giant foxtail at the other site. Our results support the idea that remote sensing has potential for weed detection in soybean, particularly when weed management systems do not require differentiation among weed species. Additional research is needed to characterize the effect of weed density or cover and crop–weed phenology on classification accuracies. Nomenclature: Sethoxydim; giant foxtail, Setaria faberi Herrm. #3 SETFA; velvetleaf, Abutilon theophrasti Medicus # ABUTH; soybean, Glycine max (L.) Merr. ‘Asgrow 2733’. Additional index words: Precision farming, site-specific agriculture, weed maps. Abbreviations: ACRE, Agronomy Center for Research and Education; DPAC, Davis-Purdue Agricultural Research Center; FLL, Fisher linear likelihood; MED, minimum Euclidian distance; SAM, spectral angle mapper; SSWM, site-specific weed management.

[1]  J. Streibig,et al.  Herbicides – a two‐edged sword* , 2003 .

[2]  Susan Eitelman,et al.  Matlab Version 6.5 Release 13. The MathWorks, Inc., 3 Apple Hill Dr., Natick, MA 01760-2098; 508/647-7000, Fax 508/647-7001, www.mathworks.com , 2003 .

[3]  L. Wiles,et al.  Spatial Distribution of Broadleaf Weeds in North Carolina Soybean (Glycine max) Fields , 1992, Weed Science.

[4]  Lei Tian,et al.  AERIAL CIR REMOTE SENSING FOR WEED DENSITY MAPPING IN A SOYBEAN FIELD , 2001 .

[5]  R. Cousens,et al.  Theory and reality of weed control thresholds [review]. [Symposium paper] , 1987 .

[6]  Lei Tian,et al.  IN-FIELD VARIABILITY DETECTION AND SPATIAL YIELD MODELING FOR CORN USING DIGITAL AERIAL IMAGING , 1999 .

[7]  Gail G. Wilkerson,et al.  Software for Mapping and Analyzing Weed Distributions: gWeedMap , 1998 .

[8]  P. J. Pinter,et al.  Remote sensing for crop protection , 1993 .

[9]  S. E. White,et al.  Using precision farming technologies to improve management of soil and fertiliser nitrogen , 1998 .

[10]  Gaines E. Miles,et al.  MACHINE VISION AND IMAGE PROCESSING FOR PLANT IDENTIFICATION. , 1986 .

[11]  Lawrence W. Lass,et al.  Detection of Yellow Starthistle (Centaurea solstitialis) and Common St. Johnswort (Hypericum perforatum) with Multispectral Digital Imagery , 1996, Weed Technology.

[12]  Lamb,et al.  Evaluating the accuracy of mapping weeds in fallow fields using airborne digital imaging: Panicumeffusum in oilseed rape stubble , 1998 .

[13]  A. J. Richardson,et al.  Light Reflectance and Remote Sensing of Weeds in Agronomic and Horticultural Crops , 1985, Weed science.

[14]  David Lamb,et al.  PA—Precision Agriculture: Remote-Sensing and Mapping of Weeds in Crops , 2001 .

[15]  Lawrence W. Lass,et al.  Detection of Yellow Hawkweed (Hieracium pratense) with High Resolution Multispectral Digital Imagery , 1995, Weed Technology.

[16]  J. V. Stafford,et al.  Potential for automatic weed detection and selective herbicide application , 1991 .

[17]  R. B. Brown,et al.  Site specific weed management with a direct-injection precision sprayer. , 2000 .

[18]  James H. Everitt,et al.  Using Satellite Data to Map False Broomweed (Ericameria austrotexana) Infestations on South Texas Rangelands , 1993, Weed Technology.

[19]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[20]  T. N. Jordan.  A survey of problem weeds in Indiana. , 1980 .

[21]  J. Peñuelas,et al.  Remote sensing of biomass and yield of winter wheat under different nitrogen supplies , 2000 .

[22]  J. V. Stafford,et al.  Spatially variable treatment of weed patches , 1996 .

[23]  J. V. Stafford,et al.  Selective application of herbicides to UK cereal crops. , 1990 .

[24]  D. Weisenburger.  Human health effects of agrichemical use. , 1993, Human pathology.

[25]  R. Hobbs,et al.  Fragmentation, Disturbance, and Plant Distribution: Mistletoes in Woodland Remnants in the Western Australian Wheatbelt , 1995 .

[26]  Shiv O. Prasher,et al.  HYPERSPECTRAL IMAGE CLASSIFICATION TO DETECT WEED INFESTATIONS AND NITROGEN STATUS IN CORN , 2003 .

[27]  J. V. Stafford,et al.  A hand-held data logger with integral GPS for producing weed maps by field walking , 1996 .

[28]  John B. Solie,et al.  Effect of row spacing, growth stage, and nitrogen rate on spectral irradiance in winter wheat , 2000 .

[29]  J. Steckler,et al.  Prescription maps for herbicide sprayer control. , 1993 .

[30]  A. J. Richardson,et al.  Distinguishing weed from crop plants using video remote sensing , 1985 .

[31]  Rew,et al.  Evaluating the accuracy of mapping weeds in seedling crops using airborne digital imaging: Avena spp. in seedling triticale , 1999 .

[32]  J. Everitt,et al.  Using Remote Sensing to Distinguish Common (Isocoma coronopifolia) and Drummond Goldenweed (Isocoma drummondii) , 1992, Weed Science.

[33]  G. W. Cussans,et al.  A technique for mapping the spatial distribution of Elymus repots, with estimates of the potential reduction in herbicide usage from patch spraying , 1996 .

[34]  R. B. Brown,et al.  Weed patch identification in no-till corn using digital imagery , 1993 .

[35]  J. De Baerdemaeker,et al.  Weed Detection Using Canopy Reflection , 2002, Precision Agriculture.

[36]  Robert M. Hayes,et al.  Economic Analysis of Alternative Herbicide Regimes on Roundup Ready Soybeans , 1999 .

[37]  F. E. LaMastus,et al.  Using remote sensing to detect weed infestations in Glycine max , 2000, Weed Science.

[38]  B. R. Roberts,et al.  RELATIONSHIPS BETWEEN REMOTELY SENSED REFLECTANCE DATA AND COTTON GROWTH AND YIELD , 2000 .

[39]  James S. Schepers,et al.  Aerial Photography to Detect Nitrogen Stress in Corn , 1996 .