Resumen
In an analysis of the penetration resistance and tillage depth of post-tillage soil, four surface-layer discrimination methods, specifically, three machine learning algorithms?Kmeans, DBSCAN, and GMM?and a curve-fitting method, were used to analyze data collected from the cultivated and uncultivated layers. Among them, the three machine learning algorithms found the boundary between the tilled and untilled layers by analyzing which data points belonged to which layer to determine the depth of the soil in the tilled layer. The curve-fitting method interpreted the intersection among data from the fitted curves of the ploughed layer and the un-ploughed layer as the tillage depth. The three machine learning algorithms were used to process a standard data set for model evaluation. DBSCAN?s discrimination accuracy of this data set reached 0.9890 and its F1 score reached 0.9934, which were superior to those of the other two algorithms. Under standard experimental conditions, the ability of DBSCAN clustering to determine the soil depth was the best among the four discrimination methods, and the discrimination accuracy reached 90.63% when the error was 15 mm. During field-test verification, the discriminative effect of DBSCAN clustering was still the best among the four methods. However, the soil blocks encountered in the field test affected the test data, resulting in large errors in the processing results. Therefore, the combined RANSCA robust regression and DBSCAN clustering algorithm, which can eliminate interference from soil blocks in the cultivated layer and can solve the problem of large depth errors caused by soil blocks in the field, was used to process the data. After testing, when the RANSCA and DBSCAN combined method was used to process all samples in the field and the error was less than 20mm, the accuracy rate reached 82.69%. This combined method improves the applicability of discrimination methods and provides a new method of determining soil depth.