Genus-Physiognomy-Ecosystem (GPE) System for Satellite-Based Classification of Plant Communities

Abstract

Vegetation mapping and monitoring is important as the composition and distribution of vegetation has been greatly influenced by land use change and the interaction of land use change and climate change. The purpose of vegetation mapping is to discover the extent and distribution of plant communities within a geographical area of interest. The paper introduces the Genus-Physiognomy-Ecosystem (GPE) system for the organization of plant communities from the perspective of satellite remote sensing. It was conceived for broadscale operational vegetation mapping by organizing plant communities according to shared genus and physiognomy/ecosystem inferences, and it offers an intermediate level between the physiognomy/ecosystem and dominant species for the organization of plant communities. A machine learning and cross-validation approach was employed by utilizing multi-temporal Landsat 8 satellite images on a regional scale for the classification of plant communities at three hierarchical levels: (i) physiognomy, (ii) GPE, and (iii) dominant species. The classification at the dominant species level showed many misclassifications and undermined its application for broadscale operational mapping, whereas the GPE system was able to lessen the complexities associated with the dominant species level classification while still being capable of distinguishing a wider variety of plant communities. The GPE system therefore provides an easy-to-understand approach for the operational mapping of plant communities, particularly on a broad scale.

1. Introduction

Plant communities are distinguishable patches of plant species formed within an area through the interaction of biotic and abiotic factors [1,2,3]. The distribution and composition of plant communities has been greatly influenced by land use history [4,5], and the interaction of land use change and climate change has much intensified the impacts on plant communities [6,7]. The organization and monitoring of plant communities is necessary to better understand the mechanisms of vegetation changes in response to global change.

Traditionally, vegetation maps of several parts of the world have been produced by manual delineation of the occurrence and distribution of vegetation types into cartographic or geographic environments [8]. This procedure has been facilitated by the visual interpretation of aerial or satellite images [9,10]. Mapping of vegetation types in modern days involves the numerical analysis of environmental data such as temperature, precipitation, and geology and/or the classification of aerial or satellite images [11,12,13]. Machine learning of remote sensing images with a small set of ground truth data and the construction of a model to predict unseen data has been a common practice for producing vegetation maps. Researchers have tried many sorts of remote sensing images, multi-spectral and hyper-spectral images obtained from satellites or aircrafts, for the classification and mapping of vegetation types [14,15,16]. A number of machine learning classifiers, support vector machines, random forests, and neural networks have been employed for this purpose [17,18,19,20]. The organization and mapping of plant communities is necessary to inform the occurrence and distribution of vegetation types in a region of interest [21,22].

Vegetation mapping involves two procedures: (i) organization of plant communities from a biogeographical or ecological point of view and (ii) delineation or mapping of plant communities into cartographic or geographic environments. The word classification is reserved for classifying the satellite images, and word organization is used for the classification of plant communities. Intensive field surveys have been done by pioneer researchers to identify and organize vegetation types in different parts of the world [23,24,25]. Some typical systems for the organization of vegetation types are summarized as follows:

(i)

Bioclimate [26,27]: This is mainly the effects of temperature and precipitation. For example, tropical rain forests, boreal forests, Arctic meadows, etc.;

(ii)

Ecosystem [28]: Associated ecological significance, such as alpine herbaceous, wetland herbaceous, etc.;

(iii)

Physiognomy [29,30,31]: Physical appearance and structure (needle-leaved or broad-leaved), phenology (deciduous or evergreen), and life form (tree, shrub, or herb). For example, Evergreen Broadleaf Forest, Evergreen Conifer Forest, Deciduous Broadleaf Forest, Deciduous Conifer Forest, shrubland, and herbaceous;

(iv)

Phytosociological association [32]: Association of characteristic species, such as Saso kurilensis-Fagetum crenatae;

(v)

Community dominance [33]: Presence of dominant species, such as Abies mariesii, Fagus crenata, Quercus crispula, Quercus serrata, Sasa kurilensis, etc.

From the perspective of satellite remote sensing, among these five typical systems for the organization of plant communities (bioclimate, ecosystem, physiognomy, phytosociological association, and dominant species), the phytosociological association system, which is based on characteristic species rather than dominant species, is different because the dominant species mostly determine the measured physical signals. In addition, the bioclimatic variables are not relevant to the mapping of vegetation types at finer spatial resolutions as they are available at coarse spatial resolutions. Physiognomy and ecosystems are quite higher levels that cannot inform about the detailed composition of vegetation types. Dominant species should be a final level of vegetation mapping. However, particularly on a broad scale, the enumeration of hundreds of dominant species is a cumbersome procedure, and the classification of satellite images for many classes is very challenging. Therefore, to cope with these limitations, an intermediate level, namely Genus-Physiognomy-Ecosystem (GPE), between the physiognomy/ecosystem and dominant species has been introduced in the research for organizing plant communities. This paper assesses the potential of the GPE system for the classification of plant communities by employing machine learning techniques on the multi-temporal Landsat 8 satellite images. The possible advantages of the GPE system for the broadscale operational mapping of plant communities are also discussed in this paper.

2. Materials and Methods

2.1. Study Area

This research was conducted in the Tohoku region of Japan which is located in a cool temperate zone. The location of the study area is shown in Figure 1.

2.2. Enumeration of Dominant Plants

In Japan, plant communities have been surveyed at a national scale based on phytosociological units. With reference to existing field survey data, 126 dominant plant species were enumerated in the study area as shown in

Table 1. List of the dominant plant species of the Tohoku region enumerated in the research.

1. Abies firma	33. Carpinus tschonoskii	65. Narthecium asiaticum	97. Rhynchospora alba
2. Abies homolepis	34. Castanea crenata	66. Nephrophyllidium crista-galli	98. Robinia pseudoacacia
3. Abies mariesii	35. Celtis jessoensis	67. Persicaria lapathifolia	99. Rosa rugosa
4. Abies sachalinensis	36. Cercidiphyllum japonicum	68. Phalaris arundinacea	100. Salix caprea
5. Acer crataegifolium	37. Chamaecyparis obtusa	69. Phragmites australis	101. Salix eriocarpa
6. Acer micranthum	38. Cornus controversa	70. Phragmites japonica	102. Salix gilgiana
7. Acer palmatum	39. Cryptomeria japonica	71. Phyllostachys bambusoides	103. Salix integra
8. Acer pictum	40. Dicentra peregrina	72. Phyllostachys edulis	104. Salix jessoensis
9. Acer rufinerve	41. Elaeagnus umbellata	73. Picea abies	105. Salix reinii
10. Acer tschonoskii	42. Empetrum nigrum	74. Pinus densiflora	106. Salix sachalinensis
11. Aesculus turbinata	43. Eriophorum vaginatum	75. Pinus parviflora	107. Salix subfragilis
12. Alnus hirsuta	44. Fagus crenata	76. Pinus pumila	108. Sasa kurilensis
13. Alnus japonica	45. Fagus japonica	77. Pinus thunbergii	109. Sasa palmata
14. Alnus maximowiczii	46. Festuca ovina	78. Populus nigra	110. Sasa senanensis
15. Alnus pendula	47. Fraxinus mandshurica	79. Populus suaveolens	111. Scirpus yagara
16. Alnus sieboldiana	48. Geum pentapetalum	80. Potentilla matsumurae	112. Solidago altissima
17. Amorpha fruticosa	49. Imperata cylindrica	81. Prunus grayana	113. Thuja standishii
18. Angelica ursina	50. Ischaemum anthephoroides	82. Prunus sargentii	114. Thujopsis dolabrata
19. Aralia elata	51. Juglans mandshurica	83. Prunus verecunda	115. Tilia japonica
20. Artemisia montana	52. Juncus fauriei	84. Prunus yedoensis	116. Toxicodendron vernicifluum
21. Betula ermanii	53. Larix kaempferi	85. Pterocarya rhoifolia	117. Tsuga diversifolia
22. Betula maximowicziana	54. Ledum palustre	86. Pueraria lobata	118. Typha domingensis
23. Betula platyphylla	55. Lespedeza bicolor	87. Quercus acutissima	119. Typha latifolia
24. Calystegia soldanella	56. Leymus mollis	88. Quercus dentata	120. Typha orientalis
25. Carex kobomugi	57. Machilus thunbergii	89. Quercus crispula	121. Ulmus davidiana
26. Carex limosa	58. Magnolia obovata	90. Quercus myrsinifolia	122. Weigela hortensis
27. Carex middendorffii	59. Menyanthes trifoliata	91. Quercus salicina	123. Zelkova serrata
28. Carex omiana	60. Miscanthus sacchariflorus	92. Quercus serrata	124. Zizania latifolia
29. Carex scabrifolia	61. Miscanthus sinensis	93. Quercus variabilis	125. Zoysia japonica
30. Carex thunbergii	62. Moliniopsis japonica	94. Reynoutria sachalinensis	126. Zoysia macrostachya
31. Carpinus cordata	63. Morus australis	95. Rhododendron degronianum
32. Carpinus laxiflora	64. Myrica gale	96. Rhododendron tschonoskii

.

Geolocations (longitudes and latitudes) of the dominant species were prepared with reference to existing survey data, visual interpretation of time-lapse images available in Google Earth, and confirmation with field observations. For each dominant species, 30–90 sample points were collected as the ground truth data from a homogenous area of at least 30 × 30 m and were distributed throughout the study area. The distribution of the ground truth data in the Tohoku region is shown in Figure 2.

2.3. Genus-Physiognomy-Ecosystem (GPE) System

On the basis of field observations in different locations in the Tohoku region, the Genus-Physiognomy-Ecosystem (GPE) system has been conceived by introducing the genus and physiognomy/ecosystem inferences on the dominant species. The GPE is an intermediate level between the physiognomy/ecosystem and the dominant species for organizing plant communities. The GPE system is more detailed than the physiognomy/ecosystem level but simpler and more practical than the dominant species level.

Table 2. Implementation of genus and physiognomy/ecosystem inferences on the dominant species.

Dominant Species	Physiognomy/Ecosystem	GPE	Inference
Acer micranthum	Shrub	Acer Shrub	Genus-Physiognomy
Acer palmatum	DBF	Acer DBF	Genus-Physiognomy
Acer pictum	DBF	Acer DBF	Genus-Physiognomy
Acer tschonoskii	Shrub	Acer Shrub	Genus-Physiognomy
Calamagrostis arundinacea	Herb/Alpine	Alpine Herb	Physiognomy-Ecosystem
Calamagrostis matsumurae	Herb/Alpine	Alpine Herb	Physiognomy-Ecosystem
Calamagrostis purpurea	Herb/Alpine	Alpine Herb	Physiognomy-Ecosystem
Miscanthus sacchariflorus	Herb	Miscanthus Herb	Genus-Physiognomy
Miscanthus sinensis	Herb	Miscanthus Herb	Genus-Physiognomy
Phragmites australis	Herb/Wetland	Wetland Herb	Physiognomy-Ecosystem
Phragmites japonica	Herb/Wetland	Wetland Herb	Physiognomy-Ecosystem
Pinus densiflora	ECF	Pinus ECF	Genus-Physiognomy
Pinus parviflora	ECF	Pinus ECF	Genus-Physiognomy
Pinus pumila	Shrub	Pinus Shrub	Genus-Physiognomy
Pinus thunbergii	ECF	Pinus ECF	Genus-Physiognomy
Potamogeton crispus	Herb	Wetland Herb	Physiognomy-Ecosystem
Potamogeton distinctus	Herb	Wetland Herb	Physiognomy-Ecosystem
Quercus acutissima	DBF	Quercus DBF	Genus-Physiognomy
Quercus dentata	DBF	Quercus DBF	Genus-Physiognomy
Quercus crispula	DBF	Quercus DBF	Genus-Physiognomy
Quercus crispula	Shrub	Quercus Shrub	Genus-Physiognomy
Quercus myrsinifolia	EBF	Quercus EBF	Genus-Physiognomy
Quercus salicina	EBF	Quercus EBF	Genus-Physiognomy
Quercus serrata	DBF	Quercus DBF	Genus-Physiognomy
Quercus variabilis	DBF	Quercus DBF	Genus-Physiognomy
Reynoutria sachalinensis	Herb	Wetland Herb	Physiognomy-Ecosystem
Rhododendron degronianum	Shrub	Rhododendron Shrub	Genus-Physiognomy
Rhododendron tschonoskii	Shrub	Rhododendron Shrub	Genus-Physiognomy
Sasa kurilensis	Shrub	Sasa Shrub	Genus-Physiognomy
Sasa palmata	Shrub	Sasa Shrub	Genus-Physiognomy
Sasa senanensis	Shrub	Sasa Shrub	Genus-Physiognomy
Scirpus triqueter	Herb/Wetland	Wetland Herb	Physiognomy-Ecosystem
Scirpus wichurae	Herb/Wetland	Wetland Herb	Physiognomy-Ecosystem
Typha latifolia	Herb/Wetland	Wetland Herb	Physiognomy-Ecosystem
Typha orientalis	Herb/Wetland	Wetland Herb	Physiognomy-Ecosystem

DBF: Deciduous Broadleaf Forest; EBF: Evergreen Broadleaf Forest; ECF: Evergreen Conifer Forest.

describes the implementation of genus and physiognomy/ecosystem inferences on the dominant species.

Still, the GPE system is capable of distinguishing a wider variety of plant (ecological) communities, such as Quercus Evergreen Broadleaf Forest (EBF) (subtropical to warm temperate), Quercus Deciduous Broadleaf Forest (DBF) (cool temperate), and Quercus Shrub (alpine). Furthermore, the GPE system offers several benefits over the dominant species system. For example, the same Quercus crispula in the dominant species system can be organized into two different communities (Quercus DBF and Quercus Shrub) under the GPE system. The Quercus Shrub, namely Miyamanara (in Japanese), is a noticeable shrub community in the alpine region.

The GPE system included all dominant tree genera (deciduous/evergreen and conifer/broadleaf). However, only shrub and herbaceous genera, prominent in large patches, were organized separately, such as Rhododendron Shrub and Miscanthus Herb. It seems complicated to identify prominent patches of all shrub and herbaceous genera and more difficult to discriminate them from the satellite images. Therefore, shrub and herbaceous communities were mostly organized with physiognomy/ecosystem inferences rather than the genus inference. Interestingly, physiognomy/ecosystem inferences are more relevant to the shrub and herbaceous communities from the viewpoint of ecological and conservation significance, such as Wetland Herb and Alpine Herb.

2.4. Processing of Landsat 8 Data

Landsat 8 data offer optical imagery in visible, near infrared, and shortwave and thermal infrared wavelengths. Standard terrain corrected (Level 1T) Landsat 8 Operational Land Imager (OLI) and Thermal Infrared Sensor (TIRS) scenes available from 2017 to 2019 over the Tohoku region of Japan were utilized. The Digital Numbers (DNs) delivered as 16-bit unsigned integers were calibrated into Top-Of-Atmosphere (TOA) spectral reflectance and brightness temperature (K) values for the OLI and TIRS respectively using the rescaling coefficients available in the metadata file. The clouds were removed by using separate Quality Assessment (QA) band information. Seven spectral bands (blue, green, red, near infrared, mid infrared, shortwave infrared, and thermal infrared) were extracted. The spectral bands were composited by calculating monthly median values pixel by pixel. In this way, 84 features (12 months × 7 bands) were generated for machine learning and classification.

2.5. Machine Learning and Cross-Validation

The potential of satellite remote sensing data for the classification of plant communities at three hierarchical levels—(i) physiognomy, (ii) Genus-Physiognomy-Ecosystem (GPE), and (iii) dominant species—was evaluated by employing a machine learning technique. The pixel values, corresponding to the ground truth (geolocation points) data, were extracted for the dominant species organization of plant communities. The ground truth data were merged for other organizations of plant communities. The number of ground truth data available for dominant species organization varied from 30 to 90 for each class. However, much larger numbers of ground truth data were available for the classification at higher levels (physiognomy and GPE) because they were supersets of the lower levels. The random forests classifier was employed for the classification of satellite images with the support of ground truth data. The classification performance was assessed by utilizing a 10-fold cross-validation method. The parameters of the model were fine-tuned with reference to the cross-validation accuracy. Accuracy metrics such as kappa coefficient and f1-score were utilized for the quantitative evaluation.

3. Results

3.1. Classification at Physiognomy Level

The confusion matrix computed with the 10-fold cross-validation approach is shown in Figure 3. The classification of plant communities at the physiognomy level showed higher accuracy in terms of the kappa coefficient (0.834) and f1-score (0.879).

The class-wise accuracy of the physiognomy level classification of plant communities is summarized in

Table 3. Class-wise performance of the physiognomy level classification of plant communities.

Class	Kappa	f1-Score
Deciduous Broadleaf Forest	0.829	0.891
Deciduous Conifer Forest	0.613	0.615
Evergreen Broadleaf Forest	0.901	0.904
Evergreen Conifer Forest	0.825	0.842
Herb	0.859	0.900
Shrub	0.807	0.847
Overall	0.834	0.879

. For the class-wise accuracy, the kappa coefficients varied from 0.613 to 0.912, and the f1-scores varied from 0.615 to 0.904.

3.2. Classification at Dominant Species Level

The classification of dominant species (126 classes) with the 10-fold cross-validation approach showed both a kappa coefficient and f1-score of 0.820. The overall accuracy is slightly lower than the physiognomy level classification. However, the class-wise accuracy analysis (

Table 4. Class-wise performance of dominant species level classification of plant communities. The numerical classes (1–126) correspond to the list of plant species enumerated and shown in Table 1.

Class	Kappa	Class	Kappa	Class	Kappa	Class	Kappa
1	0.856	33	0.888	65	0.697	97	0.440
2	1.000	34	0.941	66	0.941	98	0.748
3	0.841	35	0.941	67	1.000	99	0.941
4	0.874	36	0.947	68	0.712	100	0.947
5	1.000	37	0.947	69	0.856	101	0.933
6	0.941	38	0.947	70	0.798	102	0.933
7	0.816	39	0.941	71	0.496	103	0.941
8	0.370	40	0.947	72	0.622	104	0.874
9	0.747	41	0.899	73	0.888	105	1.000
10	0.692	42	0.941	74	0.856	106	0.768
11	0.780	43	1.000	75	0.856	107	0.748
12	0.530	44	0.874	76	1.000	108	0.947
13	0.941	45	0.841	77	0.552	109	1.000
14	0.664	46	1.000	78	0.734	110	0.888
15	0.941	47	0.874	79	0.874	111	0.749
16	0.888	48	0.416	80	1.000	112	0.726
17	0.776	49	0.776	81	0.888	113	0.933
18	0.613	50	0.179	82	0.888	114	0.874
19	0.760	51	0.622	83	0.664	115	0.947
20	0.832	52	0.776	84	0.888	116	1.000
21	0.776	53	0.874	85	0.425	117	0.822
22	0.585	54	0.800	86	0.822	118	0.909
23	0.822	55	0.941	87	0.899	119	0.947
24	0.933	56	0.816	88	0.664	120	1.000
25	0.605	57	1.000	89	0.458	121	0.888
26	0.495	58	0.841	90	0.665	122	1.000
27	0.760	59	0.530	91	0.888	123	0.874
28	0.664	60	0.841	92	0.856	124	0.748
29	0.760	61	0.748	93	0.947	125	0.941
30	1.000	62	0.262	94	0.799	126	0.947
31	0.888	63	0.841	95	1.000	Overall	0.820
32	0.947	64	0.947	96	0.748

) showed poor performance of the dominant species level classification for many dominant plants. Out of 126 dominant species, 45 species showed accuracy (kappa) lower than 80%, while nine species showed accuracy (kappa) lower than 60%. The classification of plant communities at the dominant species level introduced many misclassifications and undermined its application for the operational mapping of plant communities.

3.3. Classification at GPE Level

Table 5. Class-wise performance of GPE level classification of plant communities.

Class	Kappa	f1-Score	Class	Kappa	f1-Score
Abies ECF	0.861	0.866	Other Shrub	0.893	0.901
Acer DBF	0.891	0.894	Phyllostachys EBF	0.847	0.850
Acer Shrub	0.807	0.811	Picea ECF	0.947	0.947
Aesculus DBF	0.941	0.941	Pinus ECF	0.819	0.824
Alnus DBF	0.873	0.875	Pinus Shrub	0.888	0.889
Alnus Shrub	0.940	1.000	Populus DBF	0.908	0.909
Alpine Herb	0.971	0.941	Prunus DBF	0.929	0.932
Betula DBF	0.940	0.971	Pterocarya DBF	0.664	0.667
Carex Herb	0.698	0.741	Quercus DBF	0.876	0.882
Carpinus DBF	0.918	0.913	Quercus EBF	0.960	0.960
Castanea DBF	1.000	0.920	Quercus Shrub	0.941	0.941
Celtis DBF	1.000	1.000	Rhododendron Shrub	0.928	0.929
Cercidiphyllum DBF	0.941	1.000	Robinia DBF	0.748	0.750
Chamaecyparis ECF	0.776	0.741	Salix DBF	0.830	0.836
Cornus DBF	0.799	0.778	Salix Shrub	0.819	0.824
Cryptomeria ECF	0.947	0.900	Sasa Shrub	0.854	0.857
Fagus DBF	0.902	0.947	Thuja ECF	1.000	1.000
Fraxinus DBF	0.947	0.903	Thujopsis ECF	0.941	0.941
Juglans DBF	0.713	0.747	Tilia DBF	0.947	0.947
Larix DCF	0.874	0.714	Tsuga ECF	0.822	0.824
Machilus EBF	0.874	0.875	Ulmus DBF	0.941	0.941
Magnolia DBF	0.888	0.875	Weigela Shrub	0.941	0.941
Miscanthus Herb	0.880	0.889	Wetland Herb	0.855	0.865
Morus Shrub	0.874	0.882	Zelkova DBF	0.822	0.824
Myrica Shrub	0.941	0.875	Zoysia Herb	0.887	0.889
Other Herb	0.842	0.862	Overall	0.872	0.877

DBF: Deciduous Broadleaf Forest; EBF: Evergreen Broadleaf Forest; DCF: Deciduous Conifer Forest; ECF: Evergreen Conifer Forest.

shows the class-wise performance of the Genus-Physiognomy-Ecosystem (GPE) classes introduced in the research. Besides two classes (Pterocarya DBF and Carex Herb), at least 71% accuracy (kappa) was obtained for all GPE classes. Moreover, only five classes among 51 GPE classes showed accuracy (kappa) lower than 80%. The overall accuracy (kappa = 0.872; f1-score = 0.877) was also higher than that of dominant species level classification (kappa = 0.820; f1-score = 0.820).

Among the classification of six Acer species (Table 4, rows 5–10), only three species were classified with more than 80% accuracy, whereas the accuracy was very low (ranging from 0.370 to 0.747) for the other three species. These Acer species exhibit similar phenology and are difficult to discriminate separately from the spectral reflectance. When they are merged by the inference of common genus, an accuracy of 0.891 was achieved for Acer DBF (Table 5, row 2). A similar trend was obtained in almost all cases. The class-wise performance sounds important for operational mapping. The merging of similar species by the inference of genus also improved the classification of other genera with single species. For example, the average classification performance of Juglans mandshurica and Fraxinus mandshurica (Table 4) was 0.748, whereas Juglans DBF and Fraxinus DBF (Table 5) showed an average performance of 0.83.

4. Discussion

The collection of ground truth data for the supervised classification of dominant plant species is time-consuming and expensive. Plant species are mixed at the community level and finding a homogenous community of dominant species for use as the ground truth data is difficult. On the other hand, classification accuracy generally reduces with the large number of similar classes involved. Given the satellite features, the merging of similar classes can improve the performance, while the machine learning classifier cannot discern similar classes. To lessen the complexities associated with the mapping of plant communities at the dominant species level, the Genus-Physiognomy-Ecosystem (GPE) system was conceived in the research to organize the plant communities according to genus and physiognomy/ecosystem inferences.

Satellite remote sensing deals with the spectral reflectance obtained from the whole land surface, which is composed of vegetative, non-vegetative, topographic, and climatic characteristics. It should be easier to discriminate between two similar species (for example, Fagus crenata and Fagus japonica) located in different places rather than similar species located nearby, as satellite-based signals are also affected by topographic and climatic variations. Therefore, higher classification accuracies of plant communities obtained in the research might not be met during operation mapping, which has to deal with the discrimination of nearby pixels. Moreover, operational mapping involves the application of the machine learning model tuned with the given set of ground truth data to unseen new data, which may reduce the performance further.

It should be noted that the purpose of this research was not merely to extract (merge) similar classes/species as dictated by higher (lower) performance of machine learning classifiers. The overarching purpose of vegetation mapping is to discover the extent and distribution of plant communities within a geographical area of interest to meet conservation and management goals. Therefore, the GPE system involves the organization of plant communities according to ecological and conservation significance by introducing appropriate genus and physiognomy/ecosystem inferences. However, it is a flexible system in that the classes can be increased further in the future by expanding/shrinking genus/ecosystem inferences when the characteristics (spatial, spectral, and temporal resolutions) of satellite imagery and machine learning techniques advance along with the capability of improved classification and mapping. Nationwide mapping of plant communities on the basis of the GPE system is our plan for the immediate future.

5. Conclusions

This research evaluated the potential of satellite remote sensing data for the classification of plant communities at three hierarchical levels (physiognomy, Genus-Physiognomy-Ecosystem, and dominant species). The classification of 126 dominant plant species with multi-temporal satellite data in the Tohoku region of Japan showed that 45 dominant species could not be classified with accuracy (kappa) higher than 80%, while nine dominant species showed accuracy (kappa) lower than 60%. However, the GPE organization of plant communities, newly introduced in the research, showed that at least 71% accuracy (kappa) was obtained for all GPE classes besides two classes, while only 5 out of 51 classes showed accuracy (kappa) lower than 80%. The overall accuracy (kappa = 0.872; f1-score = 0.877) was also higher than that of the dominant species level classification (kappa = 0.820; f1-score = 0.820). The GPE system therefore provides a practical and easy-to-understand approach for the operational mapping and monitoring of plant communities, particularly on a broad scale.