SPDSS_Task89-2_CropLandUseClassificationProcedures_20060929

• Title: SPDSS Task 89.2 - Crop and Land Use Classification Procedures for Year 2001
• Description: This memorandum describes the activities conducted under Task 89: ‘Mapping of Irrigated Land Use and Irrigated Parcel Boundaries’ for year 2001 and complements the SPDSS Memoranda for Task 89.1 and Task 90.2. This memorandum also provides details on the methods used to conduct a number of Task 89 activities, including Task 89.3: Determine Irrigated Vs. Non-irrigated Lands, Task 89.4: Identify Crop Types In Each Polygon, Task 89.5: Review, Revision and Final Classification, and Task 89.6: Conduct Accuracy Assessment, as well as the results obtained from these activities for year 2001.
• Decision Support - Doc Type: Task Memorandum
• Date: 9/29/2006
• DSS Category: GIS
• DSS: South Platte
• Basin: South Platte
• Contract/PO #: C153960
• Grant Type: Non-Reimbursable
• Bill Number: SB01-157, HB02-1152, SB03-110, HB04-1221, SB05-084, HB06-1313, SB07-122
• Prepared By: Riverside Technology inc.

MEMO 89.2
100% 1.00
98% 0.98
96% 0
96
. ~

94% 0
94 ~
~, .

3 92% 0.92
~ x
Q 90% 0
90
. ~,
D
y 88% 0
88 ~
.
> ~
O
86%
0.86 ~
~

84% 0.84 '~
82% 0
82
.
80% 0
80
Initial Crop First Crop Second Crop Final Crop .

Classification Classification Classification
Classification
Refinement Refinement
(Overall Accuracy 89.80% 91.50% 93.50% 95.90%
+KIA 0.86 0.89 0.91 0.95

Figure 18. Overall Accuracy and Kappa Index of Agreement for Iterations of Irrigated Crops Classification
3. Comments and Concerns
Due to the differing dates of satellite imagery collected for each of the five Landsat frames covering the
SPDSS, initial accuracy assessment were performed on each Landsat frame individually (Table D. 8). Of
the five Landsat frames within the SPDSS study area, frame 33/32 contains 89% of all irrigated acreage in
the South Platte river basin and was therefore considered representative of the South Platte River Basin
for reporting purposes in this memorandum. Therefore, both the irrigated lands and the crop type
accuracy assessment results presented in Appendix D correspond to the final products for Districts 1, 2, 3,
and 64 delivered on November 30, 2004 corresponding to Landsat frame 33/32.
The high accuracies achieved in the irrigated lands and irrigated crop classifications, 96 percent, and 95
percent correspondingly, show the effectiveness of the classification procedures described in this
memorandum. Particularly important was the use of multitemporal Landsat data. In addition to this, the
irrigated lands classification benefited from a detailed photointerpretation and manual delineation of
irrigated parcel boundaries. Although labor intensive, this procedure in combination with the extensive
field verification campaign and meetings with water users yielded the high accuracy assessment obtained.
In the case of irrigated crops, the high accuracies obtained were possible in part through extensive
reference data collected throughout the SPDSS area, as well as rigorous and detailed error reduction
procedures during each step of this process.
Since the great majority of the reference data used in this project, for reasons explained in Section 2.4,
was data acquired from the FSA, the accuracy assessment procedures conducted are likely biased toward
a population consisting of valuable crops, especially in the irrigated crops classification. In the case of
the irrigated lands, although this bias still exists, the reference data obtained through photointerpretation
of dry land cover types in combination with the field verification campaign may have reduced the
magnitude of the bias towards FSA data. Nevertheless, information obtained from field campaign and
Page 27 of 45 ~R~versfde FecAnotogy, fnc.
4'JaYer Resources Errgi~ecr:np an~i CansuFlrnp