Estimation of canopy nitrogen content in winter wheat from Sentinel-2 images for operational agricultural monitoring View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2022-06-03

AUTHORS

Christian Bossung, Martin Schlerf, Miriam Machwitz

ABSTRACT

Canopy nitrogen content (CNC, kg/ha) provides crucial information for site-specific crop fertilization and the usability of Sentinel-2 (S2) satellite data for CNC monitoring at high fertilization levels in managed agricultural fields is still underexplored. Winter wheat samples were collected in France and Belgium in 2017 (n = 126) and 2018 (n = 18), analysed for CNC and S2-spectra were extracted at the sample locations. A comparison of three established remote sensing methods to retrieve CNC was carried out: (1) look-up-table (LUT) inversion of the canopy reflectance model PROSAIL, (2) Partial Least Square Regression (PLSR) and (3) nitrogen-sensitive vegetation indices (VI). The spatial and temporal model transferability to new data was rigorously assessed. The PROSAIL-LUT approach predicted CNC with a root mean squared error of 33.9 kg/ha on the 2017 dataset and a slightly larger value of 36.8 kg/ha on the 2018 dataset. Contrary, PLSR showed an error of 27.9 kg N/ha (R2 = 0.52) in the calibration dataset (2017) but a substantially larger error of 38.4 kg N/ha on the independent dataset (2018). VIs revealed calibration errors were slightly larger than the PLSR results but showed much higher validation errors for the independent dataset (> 50 kg/ha). The PROSAIL inversion was more stable and robust than the PLSR and VI methods when applied to new data. The obtained CNC maps may support farmers in adapting their fertilization management according to the actual crop nitrogen status. More... »

PAGES

1-24

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s11119-022-09918-y

DOI

http://dx.doi.org/10.1007/s11119-022-09918-y

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1148410771


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/07", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Agricultural and Veterinary Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0703", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Crop and Pasture Production", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Remote Sensing and Natural Resources Modelling Group, Environmental Research and Innovation Department (ERIN), Luxembourg Institute of Science and Technology (LIST), 4422, Belvaux, Luxembourg", 
          "id": "http://www.grid.ac/institutes/grid.423669.c", 
          "name": [
            "Remote Sensing and Natural Resources Modelling Group, Environmental Research and Innovation Department (ERIN), Luxembourg Institute of Science and Technology (LIST), 4422, Belvaux, Luxembourg"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bossung", 
        "givenName": "Christian", 
        "id": "sg:person.010027476713.13", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010027476713.13"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Remote Sensing and Natural Resources Modelling Group, Environmental Research and Innovation Department (ERIN), Luxembourg Institute of Science and Technology (LIST), 4422, Belvaux, Luxembourg", 
          "id": "http://www.grid.ac/institutes/grid.423669.c", 
          "name": [
            "Remote Sensing and Natural Resources Modelling Group, Environmental Research and Innovation Department (ERIN), Luxembourg Institute of Science and Technology (LIST), 4422, Belvaux, Luxembourg"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Schlerf", 
        "givenName": "Martin", 
        "id": "sg:person.016065361663.49", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016065361663.49"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Remote Sensing and Natural Resources Modelling Group, Environmental Research and Innovation Department (ERIN), Luxembourg Institute of Science and Technology (LIST), 4422, Belvaux, Luxembourg", 
          "id": "http://www.grid.ac/institutes/grid.423669.c", 
          "name": [
            "Remote Sensing and Natural Resources Modelling Group, Environmental Research and Innovation Department (ERIN), Luxembourg Institute of Science and Technology (LIST), 4422, Belvaux, Luxembourg"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Machwitz", 
        "givenName": "Miriam", 
        "id": "sg:person.01060364006.55", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01060364006.55"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/s11119-016-9463-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033141368", 
          "https://doi.org/10.1007/s11119-016-9463-8"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10712-018-9478-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1104349606", 
          "https://doi.org/10.1007/s10712-018-9478-y"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/ngeo325", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1036209430", 
          "https://doi.org/10.1038/ngeo325"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11119-019-09698-y", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1122700431", 
          "https://doi.org/10.1007/s11119-019-09698-y"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11120-006-9077-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1014577193", 
          "https://doi.org/10.1007/s11120-006-9077-5"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2022-06-03", 
    "datePublishedReg": "2022-06-03", 
    "description": "Canopy nitrogen content (CNC, kg/ha) provides crucial information for site-specific crop fertilization and the usability of Sentinel-2 (S2) satellite data for CNC monitoring at high fertilization levels in managed agricultural fields is still underexplored. Winter wheat samples were collected in France and Belgium in 2017 (n\u2009=\u2009126) and 2018 (n\u2009=\u200918), analysed for CNC and S2-spectra were extracted at the sample locations. A comparison of three established remote sensing methods to retrieve CNC was carried out: (1) look-up-table (LUT) inversion of the canopy reflectance model PROSAIL, (2) Partial Least Square Regression (PLSR) and (3) nitrogen-sensitive vegetation indices (VI). The spatial and temporal model transferability to new data\u00a0was rigorously assessed. The PROSAIL-LUT approach predicted CNC with a root mean squared error of 33.9\u00a0kg/ha on the 2017 dataset and a slightly larger value of 36.8\u00a0kg/ha on the 2018 dataset. Contrary, PLSR showed an error of 27.9\u00a0kg\u00a0N/ha (R2\u2009=\u20090.52) in the calibration dataset (2017) but a substantially larger error of 38.4\u00a0kg\u00a0N/ha on the independent dataset (2018). VIs revealed calibration errors were slightly larger than the PLSR results but showed much higher validation errors for the independent dataset (>\u200950\u00a0kg/ha). The PROSAIL inversion was more stable and robust than the PLSR and VI methods when applied to new data. The obtained CNC maps may support farmers in adapting their fertilization management according to the actual crop nitrogen status.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s11119-022-09918-y", 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1135929", 
        "issn": [
          "1385-2256", 
          "1573-1618"
        ], 
        "name": "Precision Agriculture", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }
    ], 
    "keywords": [
      "vegetation index", 
      "nitrogen content", 
      "crop nitrogen status", 
      "high fertilization levels", 
      "winter wheat samples", 
      "canopy nitrogen content", 
      "Sentinel-2 satellite data", 
      "crop fertilization", 
      "winter wheat", 
      "fertilization levels", 
      "fertilization management", 
      "partial least squares regression", 
      "nitrogen status", 
      "agricultural fields", 
      "Sentinel-2 images", 
      "wheat samples", 
      "agricultural monitoring", 
      "PROSAIL inversion", 
      "remote sensing methods", 
      "root mean squared error", 
      "independent datasets", 
      "farmers", 
      "wheat", 
      "fertilization", 
      "PROSAIL", 
      "sample locations", 
      "content", 
      "least squares regression", 
      "satellite data", 
      "calibration dataset", 
      "squares regression", 
      "sensing method", 
      "validation error", 
      "management", 
      "squared error", 
      "France", 
      "Belgium", 
      "index", 
      "mean squared error", 
      "location", 
      "model transferability", 
      "transferability", 
      "monitoring", 
      "crucial information", 
      "status", 
      "field", 
      "levels", 
      "maps", 
      "data", 
      "values", 
      "new data", 
      "estimation", 
      "information", 
      "dataset", 
      "samples", 
      "results", 
      "comparison", 
      "regression", 
      "method", 
      "approach", 
      "large errors", 
      "large values", 
      "error", 
      "inversion", 
      "images", 
      "calibration errors", 
      "usability", 
      "CNC", 
      "table (LUT) inversion", 
      "PLSR results", 
      "S2 spectra"
    ], 
    "name": "Estimation of canopy nitrogen content in winter wheat from Sentinel-2 images for operational agricultural monitoring", 
    "pagination": "1-24", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1148410771"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s11119-022-09918-y"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s11119-022-09918-y", 
      "https://app.dimensions.ai/details/publication/pub.1148410771"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-09-02T16:08", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220902/entities/gbq_results/article/article_943.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s11119-022-09918-y"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s11119-022-09918-y'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s11119-022-09918-y'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11119-022-09918-y'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11119-022-09918-y'


 

This table displays all metadata directly associated to this object as RDF triples.

156 TRIPLES      21 PREDICATES      98 URIs      85 LITERALS      4 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s11119-022-09918-y schema:about anzsrc-for:07
2 anzsrc-for:0703
3 schema:author N399d9cf40021465f8958cc1431bf3b20
4 schema:citation sg:pub.10.1007/s10712-018-9478-y
5 sg:pub.10.1007/s11119-016-9463-8
6 sg:pub.10.1007/s11119-019-09698-y
7 sg:pub.10.1007/s11120-006-9077-5
8 sg:pub.10.1038/ngeo325
9 schema:datePublished 2022-06-03
10 schema:datePublishedReg 2022-06-03
11 schema:description Canopy nitrogen content (CNC, kg/ha) provides crucial information for site-specific crop fertilization and the usability of Sentinel-2 (S2) satellite data for CNC monitoring at high fertilization levels in managed agricultural fields is still underexplored. Winter wheat samples were collected in France and Belgium in 2017 (n = 126) and 2018 (n = 18), analysed for CNC and S2-spectra were extracted at the sample locations. A comparison of three established remote sensing methods to retrieve CNC was carried out: (1) look-up-table (LUT) inversion of the canopy reflectance model PROSAIL, (2) Partial Least Square Regression (PLSR) and (3) nitrogen-sensitive vegetation indices (VI). The spatial and temporal model transferability to new data was rigorously assessed. The PROSAIL-LUT approach predicted CNC with a root mean squared error of 33.9 kg/ha on the 2017 dataset and a slightly larger value of 36.8 kg/ha on the 2018 dataset. Contrary, PLSR showed an error of 27.9 kg N/ha (R2 = 0.52) in the calibration dataset (2017) but a substantially larger error of 38.4 kg N/ha on the independent dataset (2018). VIs revealed calibration errors were slightly larger than the PLSR results but showed much higher validation errors for the independent dataset (> 50 kg/ha). The PROSAIL inversion was more stable and robust than the PLSR and VI methods when applied to new data. The obtained CNC maps may support farmers in adapting their fertilization management according to the actual crop nitrogen status.
12 schema:genre article
13 schema:isAccessibleForFree true
14 schema:isPartOf sg:journal.1135929
15 schema:keywords Belgium
16 CNC
17 France
18 PLSR results
19 PROSAIL
20 PROSAIL inversion
21 S2 spectra
22 Sentinel-2 images
23 Sentinel-2 satellite data
24 agricultural fields
25 agricultural monitoring
26 approach
27 calibration dataset
28 calibration errors
29 canopy nitrogen content
30 comparison
31 content
32 crop fertilization
33 crop nitrogen status
34 crucial information
35 data
36 dataset
37 error
38 estimation
39 farmers
40 fertilization
41 fertilization levels
42 fertilization management
43 field
44 high fertilization levels
45 images
46 independent datasets
47 index
48 information
49 inversion
50 large errors
51 large values
52 least squares regression
53 levels
54 location
55 management
56 maps
57 mean squared error
58 method
59 model transferability
60 monitoring
61 new data
62 nitrogen content
63 nitrogen status
64 partial least squares regression
65 regression
66 remote sensing methods
67 results
68 root mean squared error
69 sample locations
70 samples
71 satellite data
72 sensing method
73 squared error
74 squares regression
75 status
76 table (LUT) inversion
77 transferability
78 usability
79 validation error
80 values
81 vegetation index
82 wheat
83 wheat samples
84 winter wheat
85 winter wheat samples
86 schema:name Estimation of canopy nitrogen content in winter wheat from Sentinel-2 images for operational agricultural monitoring
87 schema:pagination 1-24
88 schema:productId N5fe37ebcd93c40889a6b6f058bee04d1
89 N8a1bbac7c67e4346b6df852ed32c7846
90 schema:sameAs https://app.dimensions.ai/details/publication/pub.1148410771
91 https://doi.org/10.1007/s11119-022-09918-y
92 schema:sdDatePublished 2022-09-02T16:08
93 schema:sdLicense https://scigraph.springernature.com/explorer/license/
94 schema:sdPublisher N83b9e69a679342cda75840215bffd84f
95 schema:url https://doi.org/10.1007/s11119-022-09918-y
96 sgo:license sg:explorer/license/
97 sgo:sdDataset articles
98 rdf:type schema:ScholarlyArticle
99 N22946aac1f3a48ffa4de88b6d9d2976c rdf:first sg:person.01060364006.55
100 rdf:rest rdf:nil
101 N399d9cf40021465f8958cc1431bf3b20 rdf:first sg:person.010027476713.13
102 rdf:rest Nc652fd16ba1a48919a2dc3f486b1254a
103 N5fe37ebcd93c40889a6b6f058bee04d1 schema:name dimensions_id
104 schema:value pub.1148410771
105 rdf:type schema:PropertyValue
106 N83b9e69a679342cda75840215bffd84f schema:name Springer Nature - SN SciGraph project
107 rdf:type schema:Organization
108 N8a1bbac7c67e4346b6df852ed32c7846 schema:name doi
109 schema:value 10.1007/s11119-022-09918-y
110 rdf:type schema:PropertyValue
111 Nc652fd16ba1a48919a2dc3f486b1254a rdf:first sg:person.016065361663.49
112 rdf:rest N22946aac1f3a48ffa4de88b6d9d2976c
113 anzsrc-for:07 schema:inDefinedTermSet anzsrc-for:
114 schema:name Agricultural and Veterinary Sciences
115 rdf:type schema:DefinedTerm
116 anzsrc-for:0703 schema:inDefinedTermSet anzsrc-for:
117 schema:name Crop and Pasture Production
118 rdf:type schema:DefinedTerm
119 sg:journal.1135929 schema:issn 1385-2256
120 1573-1618
121 schema:name Precision Agriculture
122 schema:publisher Springer Nature
123 rdf:type schema:Periodical
124 sg:person.010027476713.13 schema:affiliation grid-institutes:grid.423669.c
125 schema:familyName Bossung
126 schema:givenName Christian
127 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010027476713.13
128 rdf:type schema:Person
129 sg:person.01060364006.55 schema:affiliation grid-institutes:grid.423669.c
130 schema:familyName Machwitz
131 schema:givenName Miriam
132 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01060364006.55
133 rdf:type schema:Person
134 sg:person.016065361663.49 schema:affiliation grid-institutes:grid.423669.c
135 schema:familyName Schlerf
136 schema:givenName Martin
137 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016065361663.49
138 rdf:type schema:Person
139 sg:pub.10.1007/s10712-018-9478-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1104349606
140 https://doi.org/10.1007/s10712-018-9478-y
141 rdf:type schema:CreativeWork
142 sg:pub.10.1007/s11119-016-9463-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033141368
143 https://doi.org/10.1007/s11119-016-9463-8
144 rdf:type schema:CreativeWork
145 sg:pub.10.1007/s11119-019-09698-y schema:sameAs https://app.dimensions.ai/details/publication/pub.1122700431
146 https://doi.org/10.1007/s11119-019-09698-y
147 rdf:type schema:CreativeWork
148 sg:pub.10.1007/s11120-006-9077-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014577193
149 https://doi.org/10.1007/s11120-006-9077-5
150 rdf:type schema:CreativeWork
151 sg:pub.10.1038/ngeo325 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036209430
152 https://doi.org/10.1038/ngeo325
153 rdf:type schema:CreativeWork
154 grid-institutes:grid.423669.c schema:alternateName Remote Sensing and Natural Resources Modelling Group, Environmental Research and Innovation Department (ERIN), Luxembourg Institute of Science and Technology (LIST), 4422, Belvaux, Luxembourg
155 schema:name Remote Sensing and Natural Resources Modelling Group, Environmental Research and Innovation Department (ERIN), Luxembourg Institute of Science and Technology (LIST), 4422, Belvaux, Luxembourg
156 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...