{"id":406,"date":"2024-05-14T13:58:19","date_gmt":"2024-05-14T13:58:19","guid":{"rendered":"https:\/\/bolivia.mapbiomas.org\/?page_id=406"},"modified":"2024-11-29T16:37:43","modified_gmt":"2024-11-29T16:37:43","slug":"exactitud","status":"publish","type":"page","link":"https:\/\/bolivia.mapbiomas.org\/en\/exactitud\/","title":{"rendered":"Accuracy"},"content":{"rendered":"

Precision analysis of MapBiomas Bolivia Collection 2.0 is in development. At the moment an evaluation of the Mapbiomas Bolivia Collection 1.0 has been carried out.<\/p>\n\n\n\n

ACCESS TO THE COLLECTION 1.0 STATISTICS PANEL<\/a><\/p>\n\n\n\n

ESTIMATES OF THE ACCURACY OF LAND COVER MAPPING BY THE MAPBIOMAS PROJECT<\/strong><\/h4>\n\n\n\n

Accuracy analysis is the main way to evaluate the quality of mapping performed by MapBiomas. In addition to telling you what the overall hit rate is, the accuracy analysis also reveals estimates of the hit and miss rates for each assigned class. MapBiomas evaluated overall accuracy and for each use and cover class for all years between 1985 and 2023.<\/p>\n\n\n\n

Accuracy estimates were based on evaluating a sample of pixels, which we call the reference database, consisting of ~71,500 samples. The number of pixels in the reference database was predetermined using statistical sampling techniques. Each year, each pixel in the reference database was evaluated by technicians trained in visual interpretation of Landsat images. Accuracy evaluation was performed using metrics that compare the assigned class with the class evaluated by the technicians in the reference database.<\/p>\n\n\n\n

In each year, the precision analysis is carried out from the cross-tabulation of the sampled frequencies of the mapped and real classes, in the format of Table 1. The frequencies \"\"represents the number of pixels in the sample classified as class i, and evaluated as class j. \n\nThe totals in the marginal line represent the number of samples assigned as class i, while the totals in the marginal column \"\" They represent the number of samples evaluated by the technicians as class j. Table 1 is called the error matrix or confusion matrix.<\/p>\n\n\n\n

Table 1: Generic sample error matrix<\/h4>\n\n\n\n
\"\"<\/figure>\n\n\n\n

From the results in Table 1, the sample proportions in each cell of the table are estimated by \"\" \"\". The matrix of values \"\"  is then used to generate:<\/p>\n\n\n\n

    \n
  1. User precision: estimates of the fractions of pixels in the mapping, for each class, classified correctly. User precision is associated with an error of commission, which is the error made when assigning a pixel to class i, when it belongs to another class. The user precision for class i is estimated by \"\" and the error of commission \"\". These metrics are associated with the reliability of each assigned class.<\/li>\n\n\n\n
  2. Producer Accuracy: These are the sample fractions of pixels from each class correctly assigned to their classes by the classifiers. Producer precision is associated with the omission error, which occurs when we cannot assign a pixel of class j correctly. The producer precision for class j is estimated by\"\" and the error of omission \"\". These metrics are associated with the sensitivity of the classifier, that is, the ability to correctly distinguish a particular class from others.<\/li>\n\n\n\n
  3. Global precision: It is the estimate of the global correctness proportion of the classifiers. The estimate is given by \"\". The sum of the main diagonal of the proportions matrix. The complement of precision or the total error\"\" still decomposes into area disagreement and assignment disagreement1<\/a>. Area discrepancy measures the fraction of the error attributed to the amount of area incorrectly assigned to classes by the mapping, while assignment discrepancy to the proportion of displacement errors.<\/li>\n<\/ol>\n\n\n\n

    The matrix also provides estimates of the different types of errors. For example, it is possible to see through these the estimate of the composition of the area of \u200b\u200beach assigned class. Therefore, in addition to the success rate of the class assigned as forest, for example, we also estimate what fraction of these areas may be grasslands or other land cover and use classes, per year. We understand that this level of transparency informs users and maximizes the mapping potential of various types of users.<\/p>\n\n\n\n

    1- Pontius Jr, R. G., & Millones, M. (2011). Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment. International Journal of Remote Sensing, 32(15), 4407-4429.<\/a><\/p>\n\n\n\n

    \n\n\n\n

    ABOUT THE GRAPHICS<\/strong><\/strong><\/h4>\n\n\n\n

    GENERAL STATISTICS<\/strong><\/strong><\/h4>\n\n\n\n

    Show the average annual total precision and error decomposed into area and assignment disagreement.\"\"<\/p>\n\n\n\n

    Graph 1. Total annual precision graph<\/h4>\n\n\n\n

    This graph shows the total precision and total error by year. The total error is broken down into area disagreement and assignment disagreement. Precision is plotted at the top and errors at the bottom of the graph.<\/p>\n\n\n\n

    \"\"<\/figure>\n\n\n\n

    Graph 2. Error matrix<\/h4>\n\n\n\n

    This graph shows user precision, producer precision, and confusion between classes, for each year. The first shows the confusions of each assigned class. The second shows the confusions of each real class.<\/p>\n\n\n\n

    \"\"<\/figure>\n\n\n\n
    \"\"<\/figure>\n\n\n\n

    Graph 3. History of the class<\/h4>\n\n\n\n

    This chart allows you to inspect confusions for a particular class over time. User and producer precision are shown for each class, along with confusions in each year.<\/p>\n\n\n\n

    \"\"<\/figure>\n\n\n\n
    \"\"<\/figure>\n\n\n\n

    <\/p>","protected":false},"excerpt":{"rendered":"

    El an\u00e1lisis de precisi\u00f3n de la Colecci\u00f3n 2.0 de MapBiomas Bolivia est\u00e1 en desarrollo. Por el momento se ha realizado una evaluaci\u00f3n de la Colecci\u00f3n 1.0 de Mapbiomas Bolivia. ACCESO AL PANEL DE ESTAD\u00cdSTICAS DE LA COLECCI\u00d3N 1.0 ESTIMACIONES DE LA PRECISI\u00d3N DEL MAPEO DE LA COBERTURA DEL SUELO POR EL PROYECTO MAPBIOMAS El an\u00e1lisis […]<\/p>","protected":false},"author":2,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_uag_custom_page_level_css":""},"acf":[],"uagb_featured_image_src":{"full":false,"thumbnail":false,"medium":false,"medium_large":false,"large":false,"1536x1536":false,"2048x2048":false,"trp-custom-language-flag":false,"infographic":false,"team":false},"uagb_author_info":{"display_name":"Adriel Fernandes","author_link":"https:\/\/bolivia.mapbiomas.org\/en\/author\/adriel-fernandes\/"},"uagb_comment_info":0,"uagb_excerpt":"El an\u00e1lisis de precisi\u00f3n de la Colecci\u00f3n 2.0 de MapBiomas Bolivia est\u00e1 en desarrollo. Por el momento se ha realizado una evaluaci\u00f3n de la Colecci\u00f3n 1.0 de Mapbiomas Bolivia. ACCESO AL PANEL DE ESTAD\u00cdSTICAS DE LA COLECCI\u00d3N 1.0 ESTIMACIONES DE LA PRECISI\u00d3N DEL MAPEO DE LA COBERTURA DEL SUELO POR EL PROYECTO MAPBIOMAS El an\u00e1lisis…","_links":{"self":[{"href":"https:\/\/bolivia.mapbiomas.org\/en\/wp-json\/wp\/v2\/pages\/406"}],"collection":[{"href":"https:\/\/bolivia.mapbiomas.org\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/bolivia.mapbiomas.org\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/bolivia.mapbiomas.org\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/bolivia.mapbiomas.org\/en\/wp-json\/wp\/v2\/comments?post=406"}],"version-history":[{"count":12,"href":"https:\/\/bolivia.mapbiomas.org\/en\/wp-json\/wp\/v2\/pages\/406\/revisions"}],"predecessor-version":[{"id":776,"href":"https:\/\/bolivia.mapbiomas.org\/en\/wp-json\/wp\/v2\/pages\/406\/revisions\/776"}],"wp:attachment":[{"href":"https:\/\/bolivia.mapbiomas.org\/en\/wp-json\/wp\/v2\/media?parent=406"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}