## methods overview
The 2015 map is created based on Landsat 8 OLI imagery using an object-based forecasting classification method, with the 2010 LULC map used as the initial reference and updated using the 2015 imagery. This approach greatly improves efficiency by identifying and classifying only the changed areas based on the existing reference map. The image was classified using a supervised, object-based method in ArcGIS Pro. A large number of training samples were selected for each class based on high-resolution imagery. The image was segmented into objects based on spectral and spatial similarity, and the changed objects were classified using a random trees classification algorithm. Ancillary GIS data layers from the Maricopa Association of Governments, notably zoning, were used to improve accuracy. The map was manually assessed post-classification to correct misclassified areas and improve consistency. Accuracy assessment was performed using an independent set of testing data.
## raster value categories
| class_id | class_name | class_description |
|----------|------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 1 | Water | This class includes lakes, canal, and other small water bodies. |
| 2 | Asphalt/Road | This class mainly identifies transportation lines and other paved surface covered by asphalt, such as parking lots and commercial centers. This class does not typically include road segments within a residential block. |
| 3 | Concrete/Buildings | This class mainly identifies commercial and industrial buildings. It also includes concrete covered areas. |
| 4 | Urban mixture | This class identifies mixture of constructed materials, fragmented vegetation and paved surface. |
| 5 | Residential | This class includes various types of dwellings such as single-family homes in neighborhoods, apartments, mobile homes, and rural lots. |
| 6 | Residential (white rooftops) | This class identifies cluster of residential buildings that have bright (usually white) rooftops, such as aluminum roofed house trailers and foam-based flat roofing. |
| 7 | Active crop | This class identifies croplands that were covered by live, green vegetation at the time of image acquisition. |
| 8 | Inactive crop | This class identifies croplands that were not covered by live, green vegetation at the time of image acquisition. |
| 9 | Cultivated vegetation | This class includes urban green space such as golf courses and parks. |
| 10 | Natural vegetation | This class includes vegetation growing in desert or riparian area, such as shrubs. |
| 11 | Soil/Desert | This class includes bare soil, desert, and any undeveloped or open land. |
## accuracy assessment
| class_id | overall_accuracy | producer_accuracy | user_accuracy |
|------------------------------|------------------|-------------------|---------------|
| Water | 0.91 | 91% | 97.8% |
| Asphalt/Road | 0.96 | 96% | 88.1% |
| Concrete/Buildings | 0.89 | 89% | 92.7% |
| Urban mixture | 0.85 | 85% | 94.4% |
| Residential | 0.93 | 93% | 74.4% |
| Residential (white rooftops) | 0.94 | 94% | 91.3% |
| Active crop | 0.85 | 85% | 94.4% |
| Inactive crop | 0.86 | 86% | 100% |
| Cultivated vegetation | 0.84 | 84% | 81.6% |
| Natural vegetation | 0.88 | 88% | 87.1% |
| Soil/Desert | 0.89 | 89% | 82.4% |
| Overall | 0.89 | 89% | NA |
Overall accuracy is equal to Producer's accuracy as 100 testing samples were used for each land cover class
