Temporal sequence Object-based CNN(TS-OCNN) for crop classification from fine resolution remote sensing image time-series

Accurate crop distribution mapping is required for crop yield prediction and field management. Due to rapid progress in remote sensing technology, fine spatial resolution(FSR) remotely sensed imagery now offers great opportunities for mapping crop types in great detail. However, within-class variance can hamper attempts to discriminate crop classes at fine resolutions. Multi-temporal FSR remotely sensed imagery provides a means of increasing crop classification from FSR imagery, although current methods do not exploit the available information fully. In this research, a novel Temporal Sequence Object-based Convolutional Neural Network(TS-OCNN) was proposed to classify agricultural crop type from FSR image time-series. An object-based CNN(OCNN) model was adopted in the TS-OCNN to classify images at the object level(i.e., segmented objects or crop parcels), thus, maintaining the precise boundary information of crop parcels. The combination of image time-series was first utilized as the input to the OCNN model to produce an ‘original’ or baseline classification. Then the single-date images were fed automatically into the deep learning model scene-by-scene in order of image acquisition date to increase successively the crop classification accuracy. By doing so, the joint information in the FSR multi-temporal observations and the unique individual information from the single-date images were exploited comprehensively for crop classification. The effectiveness of the proposed approach was investigated using multitemporal SAR and optical imagery, respectively, over two heterogeneous agricultural areas. The experimental results demonstrated that the newly proposed TS-OCNN approach consistently increased crop classification accuracy, and achieved the greatest accuracies(82.68% and 87.40%) in comparison with state-of-the-art benchmark methods, including the object-based CNN(OCNN)(81.63% and85.88%), object-based image analysis(OBIA)(78.21% and 84.83%), and standard pixel-wise CNN(79.18%and 82.90%). The proposed approach is the first known attempt to explore simultaneously the joint information from image time-series with the unique information from single-date images for crop classification using a deep learning framework. The TS-OCNN, therefore, represents a new approach for agricultural landscape classification from multi-temporal FSR imagery. Besides, it is readily generalizable to other landscapes(e.g., forest landscapes), with a wide application prospect.

Fine-resolution forest tree height estimation across the Sierra Nevada through the integration of spaceborne LiDAR, airborne LiDAR, and optical imagery

Forests of the Sierra Nevada(SN)mountain range are valuable natural heritages for the region and the country,and tree height is an important forest structure parameter for understanding the SN forest ecosystem.There is still a need in the accurate estimation of wall-to-wall SN tree height distribution at fine spatial resolution.In this study,we presented a method to map wall-to-wall forest tree height(defined as Lorey’s height)across the SN at 70-m resolution by fusing multi-source datasets,including over 1600 in situ tree height measurements and over 1600 km^(2) airborne light detection and ranging(LiDAR)data.Accurate tree height estimates within these airborne LiDAR boundaries were first computed based on in situ measurements,and then these airborne LiDAR-derived tree heights were used as reference data to estimate tree heights at Geoscience Laser Altimeter System(GLAS)footprints.Finally,the random forest algorithm was used to model the SN tree height from these GLAS tree heights,optical imagery,topographic data,and climate data.The results show that our fine-resolution SN tree height product has a good correspondence with field measurements.The coefficient of determination between them is 0.60,and the root-mean-squared error is 5.45 m.

A novel fine-resolution snow depth retrieval model to revealdetailed spatiotemporal patterns of snow cover in NortheastChina

Seasonal snow cover is a key component of the global climate and hydrological system,it has drawn considerable attention under global warming conditions.Although several passive microwave(PMW)snow depth(SD)products have been developed since the 1970s,they inherit noticeable errors and uncertainties when representing spatial distributions and temporal changes of SD,especially in complex mountainous regions.In this paper,we developed afine-resolution SD retrieval model(FSDM)using machine learning to improve SD estimation quality for Northeast China and produced a long-term,fine-resolution,daily SD dataset.The accuracies of the FSDM dataset were evaluated against in-situ SD data along with existing SD products.The results showed the FSDM dataset provided satisfactory inversion accuracy in spatiotemporal evaluation,with the root-mean-square error(RMSE),bias,and correlation coefficient(R)of 7.10 cm,-0.13 cm,and 0.60.Additionally,we analyzed the spatiotemporal variations of SD in Northeast China and found that snow cover was mainly distributed in the Greater Khingan Range,Lesser Khingan Mountains,and Changbai Mountain regions.The SD exhibited high-low distribution patterns with the increased latitude.The annual mean SD slightly increased at the rate of 0.029 cm/year during 1987-2018.