To address the issue that traditional semi-supervised self-training classification methods can lead to dataset confusion, affecting the accuracy of subsequent small-sample tree species classification, an EW-EL(entropy weight and ensemble learning) semi-supervised small-sample tree species classification method is proposed based on the entropy weight method(EW) and ensemble learning(EL). EW-EL introduces the concept of EL into the theoretical framework of traditional semi-supervised self-training classification methods, using the entropy weight method as a foundational theory. It calculates the information entropy based on the F1 score of base classifiers in the current training cycle as a weight factor. Then, design the weights according to the idea that the larger the information entropy, the more unstabel the base classifier will be. This will make the classification probabilities of the ensemble classifier more concentrated and reduce the bias of the ensemble classifier. The findings demonstrate that, in contrast to conventional semi-supervised self-training techniques, EW-EL can efficiently balance data distribution, producing more precise pseudo-label sample categories for recently added data. With a recall of 0.96 and a Kappa coefficient of 0.97, the overall accuracy(OA) of the EW-EL method for small-sample tree species classification is 0.97. All three indicators are superior to supervised classification, conventional semi-supervised self-training techniques, and semi-supervised self-training techniques built using conventional EL mechanisms. In particular, the EW-EL approach outperforms semi-supervised self-training techniques that incorporate a soft voting mechanism in terms of OA and recall by 1%. Furthermore, in the chosen test area, the tree species map produced with EW-EL in combination with basic linear iterative clustering reached 94% accuracy. Moreover, extra analyses show that EW-EL can integrate several classifiers to provide better small-sample tree species classification results, which makes it more appropriate for relevant departments in forestry resource statistics under low-cost circumstances.
REZAEEK, MOUSAVIRADS J, KHOSRAVIM R,et al.An autonomous UAV-Assisted distance-aware crowd sensing platform using deep shufflenet transfer learning[J].IEEE Transactions on Intelligent Transportation Systems,2022,23(7):9404-9413.
[2]
GAZZEAM, KRISTENSENL M, PIROTTIF,et al.Tree species classification using high-resolution satellite imagery and weakly supervised learning[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-11.
[3]
XIY, TIANJ, JIANGH,et al.Mapping tree species in natural and planted forests using Sentinel-2 images[J].Remote Sensing Letters,Taylor & Francis,2022,13(6):544-555.
PUT, WANGN, TANGL M,et al.Adaptive integrated high-resolution tree species remote sensing classification[J].Remote Sensing Information,2023,38(6):139-147.
[6]
WANGN, PUT, ZHANGY,et al.More appropriate DenseNetBL classifier for small sample tree species classification using UAV-based RGB imagery[J].Heliyon,2023,9(10):e20467.
[7]
WANGN, PUT, CHENT.Simple linear iterative clustering and ConvNeXt for mapping vectorize tree species[J].Journal of Applied Remote Sensing,2023,17(3):038502.
[8]
FASSNACHTF E, LATIFIH, STEREŃCZAKK,et al.Review of studies on tree species classification from remotely sensed data[J].Remote Sensing of Environment,2016,186:64-87.
CHENL W, ZHOUX C, LIC X,et al.Classification of tree species based on UNet-ResNet14* semi-supervised learning using UAV images[J].Transactions of the Chinese Society of Agricultural Engineering,2024,40(1):217-226.
[11]
WANH, TANGY, JINGL,et al.Tree species classification of forest stands using multisource remote sensing data[J].Remote Sensing,,2021,13(1):144-168.
[12]
AYGUNESB, CINBISR G, AKSOYS.Weakly supervised instance attention for multisource fine-grained object recognition with an application to tree species classification[J].ISPRS Journal of Photogrammetry and Remote Sensing,2021,176:262-274.
[13]
DEURM, GAŠPAROVIĆM, BALENOVIĆI.An evaluation of pixel- and object-based tree species classification in mixed deciduous forests using pansharpened very high spatial resolution satellite imagery[J].Remote Sensing,2021,13(10):1868.
[14]
DECHESNEC, MALLETC, LE BRISA,et al.Semantic segmentation of forest stands of pure species combining airborne lidar data and very high resolution multispectral imagery[J].ISPRS Journal of Photogrammetry and Remote Sensing,2017,126:129-145.
[15]
QIH, ZHOUZ, IRIZARRYJ,et al.Automatic identification of causal factors from fall-related accident investigation reports using machine learning and ensemble learning approaches[J].Journal of Management in Engineering,2024,40(1):04023050.
[16]
YAGHOUBIE, YAGHOUBIE, KHAMEESA,et al.A systematic review and meta-analysis of artificial neural network,machine learning,deep learning,and ensemble learning approaches in field of geotechnical engineering[J].Neural Computing and Applications,2024,36(21):12655-12699.
[17]
ELSAYEDH S, SAADO M, SOLIMANM S,et al.Attention-Based fully convolutional densenet for earthquake detection[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-10.
[18]
CHENZ, YANGJ, CHENL,et al.Garbage classification system based on improved ShuffleNet v2[J].Resources,Conservation and Recycling,2022,178:106090.
[19]
KRUEANGSAIA, SUPRATIDS.Effects of shortcut-level amount in lightweight ResNet of ResNet on object recognition with distinct number of categories[C]//2022 International Electrical Engineering Congress(iEECON),Khno Kaen,Thailand,2022:1-4.
[20]
JAMALIA, ROYS K, GHAMISIP.WetMapFormer:A unified deep CNN and vision transformer for complex wetland mapping[J].International Journal of Applied Earth Observation and Geoinformation,2023,120:103333.