{"id":626,"date":"2024-02-09T17:44:56","date_gmt":"2024-02-09T17:44:56","guid":{"rendered":"https:\/\/peru.mapbiomas.org\/?page_id=626"},"modified":"2025-03-18T13:29:40","modified_gmt":"2025-03-18T18:29:40","slug":"exactitud","status":"publish","type":"page","link":"https:\/\/peru.mapbiomas.org\/en\/exactitud\/","title":{"rendered":"Accuracy"},"content":{"rendered":"

ACCURACY ASSESSMENT ANALYSIS OF MAPBIOMAS' LAND COVER AND LAND USE MAPPING<\/strong><\/h4>\n\n\n\n

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

Accuracy analysis is the main way of assessing the quality of mapping performed by Mapbiomas. In addition to telling the overall classification accuracy, the analysis also reveals the accuracy and error rate for each classified class. MapBiomas evaluated global and per-class classification accuracy for each year between 1985 and 2021.<\/p>\n\n\n\n

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

In each year, the accuracy analysis is done by cross-tabulating the sample frequencies of the mapped and real classes, in the format of Table 1. The frequencies ni,j<\/em> represent the number of pixels in the sample classified as class i, and evaluated as class j. Marginal Line Totals \"\" , represent the number of samples mapped as class i, while the column marginal totals, \"\"  , represent the number of samples that were evaluated by the technicians as class j. Table 1 is commonly called the error matrix or confusion matrix.<\/p>\n\n\n\n

Table 1: Generic sample error matrix<\/p>\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 used to estimate:<\/p>\n\n\n\n

    \n
  1. User\u2019s Accuracies: These are the estimates of the fractions of pixels, for each classified class, correctly classified. The user\u2019s accuracy is associated with the error of commission, which is the error of assigning a pixel to class i, when it belongs to some other class. The user\u2019s accuracy for class i is estimated by \"\" and the commission error by \"\". These metrics are associated with the reliability of each classified class. <\/li>\n\n\n\n
  2. Producer\u2019s Accuracies: Are the sample fraction of pixels of each land cover\/use class correctly assigned to their classes by the classifiers. The producer's accuracy is associated with the omission error, which occurs when we fail to map a class j pixel correctly. The producer 's accuracy for class j is estimated by \"\" and the omission error by \"\". These metrics are associated with the sensitivity of the classifier, that is, the ability to correctly distinguish one class from another.<\/li>\n\n\n\n
  3. Global Accuracy: It is the estimate of the overall hit rate. The estimate is given by \"\", the sum of the main diagonal of the proportions matrix. The complement of the total accuracy, or the total error \"\" is still decomposed into area (or quantity) disagreement and allocation disagreement1<\/a>Area disagreement measures the fraction of the error attributed to the amount of area allocated incorrectly to the classes by the mapping, while the mismatch allocation to the ratio of class-displacement errors.<\/li>\n<\/ol>\n\n\n\n

    The matrix also provides estimates of the different types of errors. For example, we show estimates of true class area composition in each mapping class. Thus, in addition to the hit rate of the class mapped as forest, for example, we also estimate the fraction of these areas that could be pasture or other classes of cover and land use, for each year. We understand that this level of transparency informs users and maximizes the potential of use across multiple 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><\/h4>\n\n\n\n

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

    They show the mean annual total accuracy and the error, decomposed in area and allocation disagreements.\"\"<\/p>\n\n\n\n