https://orcid.org/0000-0003-2544-4487
![Sample our Environment & Agriculture journals, sign in here to start your access, latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5934/TOC-Subject-Sample-2021-Environment-Agriculture.jpg"})
ABSTRACT
Accurate and reliable parcel-level apple orchard mapping is required for many precise agriculture application models, including planting suitability evaluation, standardized production, and personal agricultural operation loan approval. However, in hilly areas where smallholder management predominates, the highly fragmented and heterogeneous agricultural landscape means that fine parcel-level apple orchard mapping remains challenging. This paper proposes a parcel-level apple orchard mapping method based on feature-level spatiotemporal data fusion, which is suitable for hilly areas where smallholder management predominates. First, a hierarchical strategy that simulates human image cognition processing was used to extract redundant candidate parcels from a very high spatial resolution (VHR) image (Google Earth image with a spatial resolution of 0.6 m). Second, deep learning models, including a Depth-wise Asymmetric Bottleneck Network (DABNet) and long short-term memory (LSTM), were used to extract implicit spatial and time series features of the parcels. Third, the implicit features extracted by the deep learning models were formatted into meta-features, which then formed the feature space together with the morphological and geographical features of the parcel. Fourth, based on the constructed parcel feature space, a random forests (RF) model was used to classify candidate parcels. The experiment was carried out in the town of Guanli, southwest of Qixia city, Shandong Province, China: 21,123 apple orchard parcels were extracted from 31,235 candidate parcels. The overall accuracy (OA) of the parcel-level mapping result was 0.919. The parcel features were combined according to their types, and the performance of different feature combinations for parcel classification was further compared, demonstrating that the proposed meta-features had a stronger spatial information description capability than traditional features. Moreover, the mean decrease in the accuracy (MDA) index was used to evaluate the importance of each feature. And spatial-information-related meta-features were revealed to play the most important role in parcel classification. This method provides methodological references for parcel-level orchard mapping in hilly areas where smallholder management predominates and can be applied to improve the monitoring of orchards in such areas.
Nomenclature
| DAB | = | Depth-wise asymmetric bottleneck |
| DABNet | = | Depth-wise asymmetric bottleneck network |
| DL | = | Deep learning |
| DT | = | Decision tree |
| F-pixel | = | Feature pixel |
| GLCM | = | Gray level cooccurrence matrix |
| GSF | = | General spatial features |
| GT | = | Ground truth |
| IDN | = | Independent distribution number |
| IFD | = | Independent F-pixels distribution |
| LSTM | = | Long short term memory |
| MDA | = | mean decreases in accuracy |
| MF | = | Meta-feature |
| MIDF | = | Maximum independent distribution fraction |
| NDVI | = | Normalized difference vegetation index |
| OA | = | Overall accuracy |
| PA | = | Producer’s accuracy |
| PIF | = | Parcel intrinsic feature |
| RCF | = | Richer Convolutional Features |
| RF | = | Random forest |
| RNN | = | Recurrent neural network |
| SMF | = | Spatial meta-feature |
| TMF | = | time series meta-feature |
| UA | = | User’s accuracy |
| VHR | = | Very high spatial resolution |
Disclosure statement
No potential conflict of interest was reported by the author(s).
Correction Statement
This article has been corrected with minor changes. These changes do not impact the academic content of the article.