| The spatial distribution information of crop type is important basic data for crop growth monitoring,crop yield estimation,crop planting pattern adjustment and optimization,agricultural climate and ecology modelling.Since different crop type has its specific growing pattern and phenological characteristics,how to make full use of such crop seasonal dynamics characteristics has become the key factor to distinguish one specific crop from other crops and green vegetation.Due to the influence of human behaviors,the phenomenon that same crop has different spectral signature and different crop shares similar spectral signature was very common.Therefore,how to improve the accuracy of crop mapping has become one of the most important scientific questions in the field of land cover and land use.An approach integrating object-based image analysis with random forest(RF)for mapping in-season crop types based on multi-temporal GaoFen satellite data with a spatial resolution of 16 meters was presented.A multiresolution local variance strategy was used to create crop objects,and then object-based spectral/textural features and vegetation indices were extracted from those objects.The RF classifier was employed to identify different crop types at four crop growth seasons by integrating available features.The crop classification performance of different seasons was assessed by calculating F-score values.Results show that crop maps derived using seasonal features achieved an overall accuracy of more than 87%.Compared to the use of spectral features,a feature combination of in-season textures and multi-temporal spectral and vegetation indices performs best when classifying crop types.Spectral and temporal information is more important than texture features for crop mapping.However,texture can be essential information when there is insufficient spectral and temporal information(e.g.,crop identification in the early spring).These results indicate that an object-based image analysis combined with random forest has considerable potential for in-season crop mapping using high spatial resolution imagery.The statistical measurement z-score was used to ensure compatibility with objects.We assessed the feasibility of a z-score method,and then ranked and reduced input features using a backward elimination technique.The results showed that separability can be efficiently estimated based on z-score values,and the near infrared band performed the best for crop classification.A straightforward trend was observed,and the optimal feature set was created,which was a combination of spectral,temporal,texture information and vegetation indices.These features complement one another to help increase crop map accuracy.For the 40%of the entire sample sizes,the optimal feature sets produced the best tradeoff between the number of inputs and classification accuracy,with the misclassification error of 7.09%.Additionally,reliable crop maps were obtained,with the overall accuracy of 92.64%,and the z-score method showed great potential for the separability of crops at object scale using remotely sensed multi-temporal data.We conducted spatio-temporal analyses of NEC’s major rice production region,the Heilongjiang Province,by using satellite-derived rice cultivation maps.We found that the total cultivated area of rice in Heilongjiang Province increased largely from 1993 to 2011 and it expanded spatially to the northern and eastern part of the Sanjiang Plain.The results also showed that rice cultivation areas experienced a larger increase in the region managed by the Reclamation Management Bureau(RMB)than in that managed by the local provincial government.Rice cultivation changes were closely related with those geographic factors over the investigated periods,represented by the geomorphic(slope),climatic(accumulated temperature),and hydrological(watershed)variables.These findings provide clear evidence that crop cultivation in NEC has modified to better cope with the global change. |
PDF Full Text Request