SlideShare a Scribd company logo
1
Student: Geserbaatar
Nandin-erdene
Supervisor: Prof. Kenlo
Nishida Nasahara
16th
March, 2022
Estimation of the Above-ground Biomass
and Carbon Stock in Boreal Forest Using
Satellite Data with Machine Learning
Outline
1. Introduction
2. Research objectives
3. Materials and methods
4. Data analysis and results
5. Conclusion
2
1. Introduction
3
Source: National Forest Inventory of Mongolia & Forest loss (Hansen et al., 2013 )
Boreal forest covers
about 9.2% of the total
area of Mongolia.
But those forests are
decreasing.
2020
2001
Forest area
(1000 ha)
Growing stock
(million m3
)
1990 14352.0 1382.2
2000 14263.9 1373.3
2010 14183.9 1365.4
2015 14178.3 1365.3
2020 14172.7 1364.6
Source: Global forest resources assessment 2020
4
Table 1. Boreal forest area change 1990 - 2020
Both area and stock of forests have been declining for the past 30 years!
Decreasing! Decreasing!
1.1 Introduction (cont’d)
5
Forest loss is mostly due to
fire and insects!!
1.2 Introduction (cont’d) Forest loss
Forest fire and insect damages
1.3 Introduction (cont’d)
6
Current situation of forest data in Mongolia
--- Have to be updated every 5 years in all forested area
--- Use field measurement and allometric equation
--- Spend more time, challenging to reach some area, and costly
2. Research objectives
Main objective:
To map forest above-ground biomass and carbon stock using satellite data with
machine learning
Goals:
➢ To develop a suitable model
➢ To estimate forest above-ground biomass (AGB)
➢ To evaluate boreal forest carbon stock
7
8
3. Materials and Methods
3.1 Study area
3.2 Field data
3.3 Satellite data
3.4 Methodology
3.1 Study area
9
Location: Latitude: 47°N - 53°N,
Longitude: 96° E - 104°E
Climate: Average annual rainfall
270 mm, and annual mean
temperature around 1.3 °C
Climate classification: Dwc
(continental, dry winter, cold
summer)
Total area: 20466182 ha
Forested area: 9380532 ha (45.8%)
Source: Environmental information center (www.eic.mn )
10
3.2 Field data
The distribution of field data
Plot arrangement
Total field plots in study area = 5720
AGB (Mg/ha) 1 - 50 50 - 100 100 - 150 150 - 200 200 - 250
Number of plot 1952 2570 1017 170 11
Average AGB (Mg/ha) 69.7
Number of plots
r = 6m DBH 6 cm - 14.9 cm
r = 12m DBH 15 cm - 29.9 cm
r = 20m DBH ≥ 30 cm
Note: Diameter breast height (DBH)
Source: Multi-purpose national forest inventory, Forest Resource Development Center
3.3 Satellite data
11
Satellite name Part / Row Time
Landsat 8 OLI
p133r25, p133r27
p133r26
p134r25, p134r26, p134r27
p135r24, p135r25, p135r26, p135r27
p136r24, p136r25, p136r26, p136r27
p137r24
p137r25
p137r26
p138r25, p138r26
2014 September 10
2013 September 7
2014 September 1
2013 September 5
2019 August 28
2017 August 29
2020 September 6
2015 July 23
2018 September 8
ALOS-2 / PALSAR 2
N47E100, 101, 102
N48E098, 099, 100, 101, 102, 103, 104
N49E098, 099, 100, 101, 102, 103, 104
N50E096, 097, 098, 099,100, 101, 102, 103, 104
N51E097, 098, 099, 100, 101, 102, 103, 104
N52E097, 098, 099, 100, 101, 102
N53E098, 099
2015
Table 2. Collected satellites data
12
3.4 Methodology
13
4. Data analysis and results
4.1 Input features for machine learning (ML)
4.2 Accuracy of forest above-ground biomass (AGB) prediction
4.3 Hyperparameter values of ML algorithms
4.4 Feature importance for random forest (RF)
4.5 Predicted map derived from RF model
4.6 Reference data errors
14
4.1 Input features for machine learning (ML)
Landsat 8 OLI
B2 - blue band
B3 - green band
B4 - red band
B5 - NIR
B6 - SWIR1
B7 - SWIR2
Normalised difference vegetation index (NDVI) NDVI = (NIR - red) / (NIR + red)
Normalised difference water index (NDWI) NDWI = (NIR - SWIR 1) / (NIR + SWIR 1)
Green leaf index (GLI) GLI = (2 * green - red - blue) / (2 * green + red + blue)
Enhanced vegetation index (EVI) EVI = 2.5 * (NIR - red) / (NIR + 6 * red - 7.5 * blue + 1)
Enhanced vegetation index 2 (EVI2) EVI2 = 2.5 * (NIR - red) / (NIR + 2.4 * red + 1)
Soil adjusted vegetation index (SAVI) SAVI = ((NIR - red) / (NIR + red + 0.5)) * 1.5
Ratio vegetation index (RVI) RVI = NIR / red
Difference vegetation index (DVI) DVI = NIR - red
Green normalised vegetation index (GNDVI) GNDVI = (NIR - green) / (NIR + green)
ALOS-2 / PALSAR 2
HH polarization
HV polarization
Ratio HH and HV (HH/HV)
Ratio HV and HH (HV/HH)
Difference HH and HV (HH - HV)
Radar forest degradation index (RFDI) RFDI = (HH - HV) / (HH + HV)
Topographic data
Digital Elevation Model (DEM), Slope, Aspect
Table 3. Input features
15
4.2 Accuracy of forest above-ground biomass (AGB) prediction
RF (Random Forest) XGB (Extreme Gradient Boost) SVR (Support Vector Regression)
Landsat 8 OLI
ALOS-2 / PALSAR-2
Landsat 8 OLI &
ALOS-2 / PALSAR-2
Predicted
AGB
(Mg/ha)
Observed AGB (Mg/ha)
R2
: 0.235
RMSE : 33 Mg/ha
R2
: 0.106
RMSE : 36 Mg/ha
R2
: 0.24
RMSE : 33 Mg/ha
R2
: 0.234
RMSE : 33 Mg/ha
R2
: 0.085
RMSE : 37 Mg/ha
R2
: 0.24
RMSE : 33 Mg/ha
R2
: 0.204
RMSE : 34 Mg/ha
R2
: 0.072
RMSE : 37 Mg/ha
R2
: 0.194
RMSE : 34 Mg/ha
16
4.2 Accuracy of forest above-ground biomass (AGB) prediction (cont’d)
LR (Linear Regression) AdaBoost DT (Decision Tree) KNN (k-Nearest Neighbor)
Landsat 8 OLI
ALOS-2 /
PALSAR-2
Landsat 8 OLI
& ALOS-2 /
PALSAR-2
Predicted
AGB
(Mg/ha)
Observed AGB (Mg/ha)
R2
: 0.195
RMSE : 34 Mg/ha
R2
: 0.01
RMSE : 38 Mg/ha
R2
: 0.151
RMSE : 35 Mg/ha
R2
: 0.171
RMSE : 35 Mg/ha
R2
: 0.096
RMSE : 36 Mg/ha
R2
: 0.187
RMSE : 34 Mg/ha
R2
: 0.149
RMSE : 35 Mg/ha
R2
: 0.075
RMSE : 37 Mg/ha
R2
: 0.162
RMSE : 35 Mg/ha
R2
: 0.204
RMSE : 34 Mg/ha
R2
: 0.075
RMSE : 37 Mg/ha
R2
: 0.20
RMSE : 34 Mg/ha
17
4.3 Hyperparameter values of ML algorithms
Algorithm
learning
_rate
max_
depth
min_samples_leaf /
min_child_weight
n_estimators
/ C value
kernel gamma
R2
(training)
R2
(testing)
RMSE
Mg/ha
LR
(Linear Regression)
NA NA NA NA NA NA 0.210 0.151 35
XGB
(Extreme Gradient Boost )
0.1 5 2 100 NA 1 0.578 0.24 33
AdaBoost
0.01 NA NA 100 NA NA 0.211 0.187 34
DT
(Decision Tree )
NA 4 30 NA NA NA 0.211 0.162 35
RF
(Random Forest)
NA 20 10 1000 NA NA 0.570 0.24 33
KNN
(k-Nearest Neighbor)
n_neighbor = 25, metric = ‘minkowski’, p = 2 0.244 0.20 34
SVR
(Support Vector Regression)
NA NA NA 500 rbf NA 0.231 0.194 34
Table 4. Configured hyperparameters for each ML
18
4.4 Feature importance for random forest (RF) model
High importance:
SWIR1 (Short-wave infrared band 1 of Landsat 8)
GLI (Green leaf index)
HV (Horizontal transmitting, vertical
receiving polarization of ALOS-2 )
DEM (Digital elevation model)
19
4.5 Predicted map derived from RF model
Forest above-ground biomass Forest carbon stock
20
4.6 Reference data errors
1. High AGB value on the sparse forest
2. Low AGB value on the dense forest
3. Plot covered by forest and non forest area
Notes: yellow number is AGB value, unit is Mg/ha, and yellow circle’s radius is 30 m.
1 2 3
Total 812 plots
Source: Bing aerial map & Google map
21
5. Conclusion
* Hyperparameter values were effectively influenced by overfitting error.
* SVR, KNN, and LR models were high R2
in only using Landsat data.
* The best regression model was RF. The coefficient of determination (R2
) was 0.24 and
RMSE was 33 Mg/ha. Forest AGB was estimated 32.5 Mg/ha - 122.5 Mg/ha and forest carbon
stock was estimated 16.5 Mg C/ha - 62.5 Mg C/ha.
* The highest importance variables were SWIR1, GLI, HV and DEM for the RF model.
* After data screening, 812 plots of reference data were errors. From data screening analysis
and my research, forest AGB data of National Forest Inventory in Mongolia was bad quality.
* In the future, reference field data need validation and update.
22
References
Dan, A. (2019). Multipurpose national forest inventory in Mongolia, 2014-2017-A tool to support sustainable forest
management. Geography, Environment, Sustainability, 12(3), 167-183.
Environmental information center. (2020). http://www.eic.mn
FAO. (2020). Global forest resources assessment 2020. FAO. http://www.fao.org/3/cb0031en/cb0031en.pdf
Hansen, M. C., P. V. Potapov, R. Moore, M. Hancher, S. A. Turubanova, A. Tyukavina, D. Thau, S. V. Stehman, S. J.
Goetz, T. R. Loveland, A. Kommareddy, A. Egorov, L. Chini, C. O. Justice, and J. R. G. Townshend. 2013.
“High-Resolution Global Maps of 21st-Century Forest Cover Change.” Science 342 (15 November): 850–53. Data
available online from: http://earthenginepartners.appspot.com/science-2013-global-forest.
FRDC. (2017). Multi-purpose national forest inventory in Mongolia
Nachin, B., & Sukhbaatar, G. (2013). Some results of forest carbon stock calculation in northern Mongolia. UNREDD.
www.unredd.net
Thank you for your attention!
23

More Related Content

What's hot

Geographic Phenomena and their Representations
Geographic Phenomena and their RepresentationsGeographic Phenomena and their Representations
Geographic Phenomena and their Representations
NAXA-Developers
 
газар зүйн зураг
газар зүйн зураг газар зүйн зураг
газар зүйн зураг Tsekeel Tsekee
 
Сургалтыг дэмжих үйл ажиллагааны судалгаа
Сургалтыг дэмжих үйл ажиллагааны судалгааСургалтыг дэмжих үйл ажиллагааны судалгаа
Сургалтыг дэмжих үйл ажиллагааны судалгаа
Сэтгэмж Цогцолбор Сургууль
 
Jishee
JisheeJishee
Jishee
Tuul Tuul
 
Газарзүй 8 Монгол орны хөрс.pptx
Газарзүй 8 Монгол орны хөрс.pptxГазарзүй 8 Монгол орны хөрс.pptx
Газарзүй 8 Монгол орны хөрс.pptx
Enkh Tseba
 
Battsengel plan 01
Battsengel plan 01Battsengel plan 01
Battsengel plan 01
hi_bmb
 
Et 2016.12.26
Et 2016.12.26Et 2016.12.26
Et 2016.12.26
GeoMedeelel
 
хандаа зайн сургалт
хандаа зайн сургалт хандаа зайн сургалт
хандаа зайн сургалт khandmaa79
 
Geomeeting jan2018
Geomeeting jan2018Geomeeting jan2018
Geomeeting jan2018
GeoMedeelel
 
Масштабын тухай
Масштабын тухайМасштабын тухай
Масштабын тухай
tsermaa48
 
Use of remote sensing techniques for nutrient studies in soil and plant _Knig...
Use of remote sensing techniques for nutrient studies in soil and plant _Knig...Use of remote sensing techniques for nutrient studies in soil and plant _Knig...
Use of remote sensing techniques for nutrient studies in soil and plant _Knig...
KnightNthebere
 
“ХҮҮХДЭД ЭЭЛТЭЙ СУРГУУЛЬ” 2012-2014
“ХҮҮХДЭД ЭЭЛТЭЙ СУРГУУЛЬ” 2012-2014    “ХҮҮХДЭД ЭЭЛТЭЙ СУРГУУЛЬ” 2012-2014
“ХҮҮХДЭД ЭЭЛТЭЙ СУРГУУЛЬ” 2012-2014
Хөвсгөл аймаг Боловсролын газар
 
газрын зургийн масштаб
газрын зургийн масштабгазрын зургийн масштаб
газрын зургийн масштабHaliun53
 
2а анги цахим
2а анги цахим2а анги цахим
2а анги цахимNaranjargal_Z
 
монгол хэл эх
монгол хэл   эхмонгол хэл   эх
Нарны аймаг, дэлхийн хөдөлгөөн хичээл
Нарны аймаг, дэлхийн хөдөлгөөн хичээлНарны аймаг, дэлхийн хөдөлгөөн хичээл
Нарны аймаг, дэлхийн хөдөлгөөн хичээлpurewdorjoo
 
Lecture 3
Lecture 3Lecture 3
Lecture 3
telmenten
 
Хялбар туршилтууд
Хялбар туршилтуудХялбар туршилтууд
Хялбар туршилтуудЧ. Алтка
 

What's hot (20)

Geographic Phenomena and their Representations
Geographic Phenomena and their RepresentationsGeographic Phenomena and their Representations
Geographic Phenomena and their Representations
 
газар зүйн зураг
газар зүйн зураг газар зүйн зураг
газар зүйн зураг
 
нарны аймаг
нарны аймагнарны аймаг
нарны аймаг
 
Сургалтыг дэмжих үйл ажиллагааны судалгаа
Сургалтыг дэмжих үйл ажиллагааны судалгааСургалтыг дэмжих үйл ажиллагааны судалгаа
Сургалтыг дэмжих үйл ажиллагааны судалгаа
 
Jishee
JisheeJishee
Jishee
 
Газарзүй 8 Монгол орны хөрс.pptx
Газарзүй 8 Монгол орны хөрс.pptxГазарзүй 8 Монгол орны хөрс.pptx
Газарзүй 8 Монгол орны хөрс.pptx
 
Battsengel plan 01
Battsengel plan 01Battsengel plan 01
Battsengel plan 01
 
интеграл
 интеграл интеграл
интеграл
 
Et 2016.12.26
Et 2016.12.26Et 2016.12.26
Et 2016.12.26
 
хандаа зайн сургалт
хандаа зайн сургалт хандаа зайн сургалт
хандаа зайн сургалт
 
Geomeeting jan2018
Geomeeting jan2018Geomeeting jan2018
Geomeeting jan2018
 
Масштабын тухай
Масштабын тухайМасштабын тухай
Масштабын тухай
 
Use of remote sensing techniques for nutrient studies in soil and plant _Knig...
Use of remote sensing techniques for nutrient studies in soil and plant _Knig...Use of remote sensing techniques for nutrient studies in soil and plant _Knig...
Use of remote sensing techniques for nutrient studies in soil and plant _Knig...
 
“ХҮҮХДЭД ЭЭЛТЭЙ СУРГУУЛЬ” 2012-2014
“ХҮҮХДЭД ЭЭЛТЭЙ СУРГУУЛЬ” 2012-2014    “ХҮҮХДЭД ЭЭЛТЭЙ СУРГУУЛЬ” 2012-2014
“ХҮҮХДЭД ЭЭЛТЭЙ СУРГУУЛЬ” 2012-2014
 
газрын зургийн масштаб
газрын зургийн масштабгазрын зургийн масштаб
газрын зургийн масштаб
 
2а анги цахим
2а анги цахим2а анги цахим
2а анги цахим
 
монгол хэл эх
монгол хэл   эхмонгол хэл   эх
монгол хэл эх
 
Нарны аймаг, дэлхийн хөдөлгөөн хичээл
Нарны аймаг, дэлхийн хөдөлгөөн хичээлНарны аймаг, дэлхийн хөдөлгөөн хичээл
Нарны аймаг, дэлхийн хөдөлгөөн хичээл
 
Lecture 3
Lecture 3Lecture 3
Lecture 3
 
Хялбар туршилтууд
Хялбар туршилтуудХялбар туршилтууд
Хялбар туршилтууд
 

Similar to Presentation 20220316 nandia

Characterizing Forest Dynamics and Carbon Biomass Assessment over Tropical P...
Characterizing Forest Dynamics and Carbon Biomass Assessment  over Tropical P...Characterizing Forest Dynamics and Carbon Biomass Assessment  over Tropical P...
Characterizing Forest Dynamics and Carbon Biomass Assessment over Tropical P...
Arief Wijaya
 
Deforestation drivers, carbon emission estimate and setting forest reference ...
Deforestation drivers, carbon emission estimate and setting forest reference ...Deforestation drivers, carbon emission estimate and setting forest reference ...
Deforestation drivers, carbon emission estimate and setting forest reference ...CIFOR-ICRAF
 
Characterizing Forest Degradation and Carbon Biomass Assessment in Tropical P...
Characterizing Forest Degradation and Carbon Biomass Assessment in Tropical P...Characterizing Forest Degradation and Carbon Biomass Assessment in Tropical P...
Characterizing Forest Degradation and Carbon Biomass Assessment in Tropical P...
CIFOR-ICRAF
 
IRJET - Study on Generation of Urban Heat Island with Increasing Urban Sprawl...
IRJET - Study on Generation of Urban Heat Island with Increasing Urban Sprawl...IRJET - Study on Generation of Urban Heat Island with Increasing Urban Sprawl...
IRJET - Study on Generation of Urban Heat Island with Increasing Urban Sprawl...
IRJET Journal
 
Characterizing Forest Degradation and Carbon Biomass Assessment in Tropical ...
Characterizing Forest Degradation and Carbon Biomass Assessment  in Tropical ...Characterizing Forest Degradation and Carbon Biomass Assessment  in Tropical ...
Characterizing Forest Degradation and Carbon Biomass Assessment in Tropical ...
CIFOR-ICRAF
 
Mangrove carbon stocks: Island's perspective
Mangrove carbon stocks: Island's perspectiveMangrove carbon stocks: Island's perspective
Mangrove carbon stocks: Island's perspective
CIFOR-ICRAF
 
2011_0728_IGARSS2011_Motohka.ppt
2011_0728_IGARSS2011_Motohka.ppt2011_0728_IGARSS2011_Motohka.ppt
2011_0728_IGARSS2011_Motohka.pptgrssieee
 
2011_0728_IGARSS2011_Motohka.ppt
2011_0728_IGARSS2011_Motohka.ppt2011_0728_IGARSS2011_Motohka.ppt
2011_0728_IGARSS2011_Motohka.pptgrssieee
 
Multi-sensor integration and mapping of the red mud spill in Kolontar, Hungary
Multi-sensor integration and mapping of the red mud spill in Kolontar, HungaryMulti-sensor integration and mapping of the red mud spill in Kolontar, Hungary
Multi-sensor integration and mapping of the red mud spill in Kolontar, Hungary
teraelement
 
LAND SURFACE TEMPERATURE AND ITS CORRELATION WITH VEGETATION COVER USING LAND...
LAND SURFACE TEMPERATURE AND ITS CORRELATION WITH VEGETATION COVER USING LAND...LAND SURFACE TEMPERATURE AND ITS CORRELATION WITH VEGETATION COVER USING LAND...
LAND SURFACE TEMPERATURE AND ITS CORRELATION WITH VEGETATION COVER USING LAND...
IRJET Journal
 
BioSAR2010-aSARcampaigninsupportofthebiomassmission.ppt
BioSAR2010-aSARcampaigninsupportofthebiomassmission.pptBioSAR2010-aSARcampaigninsupportofthebiomassmission.ppt
BioSAR2010-aSARcampaigninsupportofthebiomassmission.pptgrssieee
 
Barr et al Ecosummit presentation Oct 2012, Columbus OH
Barr et al Ecosummit presentation Oct 2012, Columbus OHBarr et al Ecosummit presentation Oct 2012, Columbus OH
Barr et al Ecosummit presentation Oct 2012, Columbus OH
Jordan Barr
 
Assessment of Forest Stock and Encroachment on Forest Land in Sonbhadra Fores...
Assessment of Forest Stock and Encroachment on Forest Land in Sonbhadra Fores...Assessment of Forest Stock and Encroachment on Forest Land in Sonbhadra Fores...
Assessment of Forest Stock and Encroachment on Forest Land in Sonbhadra Fores...
IRJET Journal
 
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
INFOGAIN PUBLICATION
 
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
INFOGAIN PUBLICATION
 
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
INFOGAIN PUBLICATION
 
Lecture for landsat
Lecture for landsatLecture for landsat
Lecture for landsat
GeoMedeelel
 
Effects of climate change and deforestation on potential of carbon sequestrat...
Effects of climate change and deforestation on potential of carbon sequestrat...Effects of climate change and deforestation on potential of carbon sequestrat...
Effects of climate change and deforestation on potential of carbon sequestrat...
World Agroforestry (ICRAF)
 
Evaluation_Soil_Properties_Different_Forests_Mid_Hills_Himachal_Himalayas.pdf
Evaluation_Soil_Properties_Different_Forests_Mid_Hills_Himachal_Himalayas.pdfEvaluation_Soil_Properties_Different_Forests_Mid_Hills_Himachal_Himalayas.pdf
Evaluation_Soil_Properties_Different_Forests_Mid_Hills_Himachal_Himalayas.pdf
SSR Institute of International Journal of Life Sciences
 
Gaofen-2 - Image data assessment.pdf
Gaofen-2 - Image data assessment.pdfGaofen-2 - Image data assessment.pdf
Gaofen-2 - Image data assessment.pdf
norhan32
 

Similar to Presentation 20220316 nandia (20)

Characterizing Forest Dynamics and Carbon Biomass Assessment over Tropical P...
Characterizing Forest Dynamics and Carbon Biomass Assessment  over Tropical P...Characterizing Forest Dynamics and Carbon Biomass Assessment  over Tropical P...
Characterizing Forest Dynamics and Carbon Biomass Assessment over Tropical P...
 
Deforestation drivers, carbon emission estimate and setting forest reference ...
Deforestation drivers, carbon emission estimate and setting forest reference ...Deforestation drivers, carbon emission estimate and setting forest reference ...
Deforestation drivers, carbon emission estimate and setting forest reference ...
 
Characterizing Forest Degradation and Carbon Biomass Assessment in Tropical P...
Characterizing Forest Degradation and Carbon Biomass Assessment in Tropical P...Characterizing Forest Degradation and Carbon Biomass Assessment in Tropical P...
Characterizing Forest Degradation and Carbon Biomass Assessment in Tropical P...
 
IRJET - Study on Generation of Urban Heat Island with Increasing Urban Sprawl...
IRJET - Study on Generation of Urban Heat Island with Increasing Urban Sprawl...IRJET - Study on Generation of Urban Heat Island with Increasing Urban Sprawl...
IRJET - Study on Generation of Urban Heat Island with Increasing Urban Sprawl...
 
Characterizing Forest Degradation and Carbon Biomass Assessment in Tropical ...
Characterizing Forest Degradation and Carbon Biomass Assessment  in Tropical ...Characterizing Forest Degradation and Carbon Biomass Assessment  in Tropical ...
Characterizing Forest Degradation and Carbon Biomass Assessment in Tropical ...
 
Mangrove carbon stocks: Island's perspective
Mangrove carbon stocks: Island's perspectiveMangrove carbon stocks: Island's perspective
Mangrove carbon stocks: Island's perspective
 
2011_0728_IGARSS2011_Motohka.ppt
2011_0728_IGARSS2011_Motohka.ppt2011_0728_IGARSS2011_Motohka.ppt
2011_0728_IGARSS2011_Motohka.ppt
 
2011_0728_IGARSS2011_Motohka.ppt
2011_0728_IGARSS2011_Motohka.ppt2011_0728_IGARSS2011_Motohka.ppt
2011_0728_IGARSS2011_Motohka.ppt
 
Multi-sensor integration and mapping of the red mud spill in Kolontar, Hungary
Multi-sensor integration and mapping of the red mud spill in Kolontar, HungaryMulti-sensor integration and mapping of the red mud spill in Kolontar, Hungary
Multi-sensor integration and mapping of the red mud spill in Kolontar, Hungary
 
LAND SURFACE TEMPERATURE AND ITS CORRELATION WITH VEGETATION COVER USING LAND...
LAND SURFACE TEMPERATURE AND ITS CORRELATION WITH VEGETATION COVER USING LAND...LAND SURFACE TEMPERATURE AND ITS CORRELATION WITH VEGETATION COVER USING LAND...
LAND SURFACE TEMPERATURE AND ITS CORRELATION WITH VEGETATION COVER USING LAND...
 
BioSAR2010-aSARcampaigninsupportofthebiomassmission.ppt
BioSAR2010-aSARcampaigninsupportofthebiomassmission.pptBioSAR2010-aSARcampaigninsupportofthebiomassmission.ppt
BioSAR2010-aSARcampaigninsupportofthebiomassmission.ppt
 
Barr et al Ecosummit presentation Oct 2012, Columbus OH
Barr et al Ecosummit presentation Oct 2012, Columbus OHBarr et al Ecosummit presentation Oct 2012, Columbus OH
Barr et al Ecosummit presentation Oct 2012, Columbus OH
 
Assessment of Forest Stock and Encroachment on Forest Land in Sonbhadra Fores...
Assessment of Forest Stock and Encroachment on Forest Land in Sonbhadra Fores...Assessment of Forest Stock and Encroachment on Forest Land in Sonbhadra Fores...
Assessment of Forest Stock and Encroachment on Forest Land in Sonbhadra Fores...
 
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
 
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
 
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
Measuring Individual Tree Height and Crown Diameter for Mangrove Trees with A...
 
Lecture for landsat
Lecture for landsatLecture for landsat
Lecture for landsat
 
Effects of climate change and deforestation on potential of carbon sequestrat...
Effects of climate change and deforestation on potential of carbon sequestrat...Effects of climate change and deforestation on potential of carbon sequestrat...
Effects of climate change and deforestation on potential of carbon sequestrat...
 
Evaluation_Soil_Properties_Different_Forests_Mid_Hills_Himachal_Himalayas.pdf
Evaluation_Soil_Properties_Different_Forests_Mid_Hills_Himachal_Himalayas.pdfEvaluation_Soil_Properties_Different_Forests_Mid_Hills_Himachal_Himalayas.pdf
Evaluation_Soil_Properties_Different_Forests_Mid_Hills_Himachal_Himalayas.pdf
 
Gaofen-2 - Image data assessment.pdf
Gaofen-2 - Image data assessment.pdfGaofen-2 - Image data assessment.pdf
Gaofen-2 - Image data assessment.pdf
 

More from GeoMedeelel

Intro mga mon_15mar22
Intro mga mon_15mar22Intro mga mon_15mar22
Intro mga mon_15mar22
GeoMedeelel
 
Developer community -remote-sensing.pptx
Developer community -remote-sensing.pptxDeveloper community -remote-sensing.pptx
Developer community -remote-sensing.pptx
GeoMedeelel
 
Intro mga mon_18feb22
Intro mga mon_18feb22Intro mga mon_18feb22
Intro mga mon_18feb22
GeoMedeelel
 
Agriculture drone intro
Agriculture drone introAgriculture drone intro
Agriculture drone intro
GeoMedeelel
 
Drone 20201216
Drone 20201216Drone 20201216
Drone 20201216
GeoMedeelel
 
Intro mga 15dec2021 (1)
Intro mga 15dec2021 (1)Intro mga 15dec2021 (1)
Intro mga 15dec2021 (1)
GeoMedeelel
 
Unisec global mongolia
Unisec global mongoliaUnisec global mongolia
Unisec global mongolia
GeoMedeelel
 
Bayanmunkh geomeeting
Bayanmunkh geomeetingBayanmunkh geomeeting
Bayanmunkh geomeeting
GeoMedeelel
 
Intro mga mon_19jan2021
Intro mga mon_19jan2021Intro mga mon_19jan2021
Intro mga mon_19jan2021
GeoMedeelel
 
Bayanmunkh geomeeting (1)
Bayanmunkh geomeeting (1)Bayanmunkh geomeeting (1)
Bayanmunkh geomeeting (1)
GeoMedeelel
 
Intro mga mon_19jan2021
Intro mga mon_19jan2021Intro mga mon_19jan2021
Intro mga mon_19jan2021
GeoMedeelel
 
Chcnav moblie mapping solution2
Chcnav moblie mapping solution2Chcnav moblie mapping solution2
Chcnav moblie mapping solution2
GeoMedeelel
 
5 d world_v5-19
5 d world_v5-19 5 d world_v5-19
5 d world_v5-19
GeoMedeelel
 
Intro mga 18may2021
Intro mga 18may2021Intro mga 18may2021
Intro mga 18may2021
GeoMedeelel
 
Intro mga 14apr2021
Intro mga 14apr2021Intro mga 14apr2021
Intro mga 14apr2021
GeoMedeelel
 
Demonstration of super map ai gis technology
Demonstration of super map ai gis technology  Demonstration of super map ai gis technology
Demonstration of super map ai gis technology
GeoMedeelel
 
Supermap gis 10i(2020) ai gis technology v1.0
Supermap gis 10i(2020) ai gis technology v1.0Supermap gis 10i(2020) ai gis technology v1.0
Supermap gis 10i(2020) ai gis technology v1.0
GeoMedeelel
 
Opening odbayar
Opening odbayarOpening odbayar
Opening odbayar
GeoMedeelel
 
Intro mga 17mar2021
Intro mga 17mar2021Intro mga 17mar2021
Intro mga 17mar2021
GeoMedeelel
 
Sibeli us geospatial
Sibeli us geospatialSibeli us geospatial
Sibeli us geospatial
GeoMedeelel
 

More from GeoMedeelel (20)

Intro mga mon_15mar22
Intro mga mon_15mar22Intro mga mon_15mar22
Intro mga mon_15mar22
 
Developer community -remote-sensing.pptx
Developer community -remote-sensing.pptxDeveloper community -remote-sensing.pptx
Developer community -remote-sensing.pptx
 
Intro mga mon_18feb22
Intro mga mon_18feb22Intro mga mon_18feb22
Intro mga mon_18feb22
 
Agriculture drone intro
Agriculture drone introAgriculture drone intro
Agriculture drone intro
 
Drone 20201216
Drone 20201216Drone 20201216
Drone 20201216
 
Intro mga 15dec2021 (1)
Intro mga 15dec2021 (1)Intro mga 15dec2021 (1)
Intro mga 15dec2021 (1)
 
Unisec global mongolia
Unisec global mongoliaUnisec global mongolia
Unisec global mongolia
 
Bayanmunkh geomeeting
Bayanmunkh geomeetingBayanmunkh geomeeting
Bayanmunkh geomeeting
 
Intro mga mon_19jan2021
Intro mga mon_19jan2021Intro mga mon_19jan2021
Intro mga mon_19jan2021
 
Bayanmunkh geomeeting (1)
Bayanmunkh geomeeting (1)Bayanmunkh geomeeting (1)
Bayanmunkh geomeeting (1)
 
Intro mga mon_19jan2021
Intro mga mon_19jan2021Intro mga mon_19jan2021
Intro mga mon_19jan2021
 
Chcnav moblie mapping solution2
Chcnav moblie mapping solution2Chcnav moblie mapping solution2
Chcnav moblie mapping solution2
 
5 d world_v5-19
5 d world_v5-19 5 d world_v5-19
5 d world_v5-19
 
Intro mga 18may2021
Intro mga 18may2021Intro mga 18may2021
Intro mga 18may2021
 
Intro mga 14apr2021
Intro mga 14apr2021Intro mga 14apr2021
Intro mga 14apr2021
 
Demonstration of super map ai gis technology
Demonstration of super map ai gis technology  Demonstration of super map ai gis technology
Demonstration of super map ai gis technology
 
Supermap gis 10i(2020) ai gis technology v1.0
Supermap gis 10i(2020) ai gis technology v1.0Supermap gis 10i(2020) ai gis technology v1.0
Supermap gis 10i(2020) ai gis technology v1.0
 
Opening odbayar
Opening odbayarOpening odbayar
Opening odbayar
 
Intro mga 17mar2021
Intro mga 17mar2021Intro mga 17mar2021
Intro mga 17mar2021
 
Sibeli us geospatial
Sibeli us geospatialSibeli us geospatial
Sibeli us geospatial
 

Recently uploaded

Climate Change All over the World .pptx
Climate Change All over the World  .pptxClimate Change All over the World  .pptx
Climate Change All over the World .pptx
sairaanwer024
 
International+e-Commerce+Platform-www.cfye-commerce.shop
International+e-Commerce+Platform-www.cfye-commerce.shopInternational+e-Commerce+Platform-www.cfye-commerce.shop
International+e-Commerce+Platform-www.cfye-commerce.shop
laozhuseo02
 
Characterization and the Kinetics of drying at the drying oven and with micro...
Characterization and the Kinetics of drying at the drying oven and with micro...Characterization and the Kinetics of drying at the drying oven and with micro...
Characterization and the Kinetics of drying at the drying oven and with micro...
Open Access Research Paper
 
Summary of the Climate and Energy Policy of Australia
Summary of the Climate and Energy Policy of AustraliaSummary of the Climate and Energy Policy of Australia
Summary of the Climate and Energy Policy of Australia
yasmindemoraes1
 
Alert-driven Community-based Forest monitoring: A case of the Peruvian Amazon
Alert-driven Community-based Forest monitoring: A case of the Peruvian AmazonAlert-driven Community-based Forest monitoring: A case of the Peruvian Amazon
Alert-driven Community-based Forest monitoring: A case of the Peruvian Amazon
CIFOR-ICRAF
 
Daan Park Hydrangea flower season I like it
Daan Park Hydrangea flower season I like itDaan Park Hydrangea flower season I like it
Daan Park Hydrangea flower season I like it
a0966109726
 
How about Huawei mobile phone-www.cfye-commerce.shop
How about Huawei mobile phone-www.cfye-commerce.shopHow about Huawei mobile phone-www.cfye-commerce.shop
How about Huawei mobile phone-www.cfye-commerce.shop
laozhuseo02
 
Prevalence of Toxoplasma gondii infection in domestic animals in District Ban...
Prevalence of Toxoplasma gondii infection in domestic animals in District Ban...Prevalence of Toxoplasma gondii infection in domestic animals in District Ban...
Prevalence of Toxoplasma gondii infection in domestic animals in District Ban...
Open Access Research Paper
 
"Understanding the Carbon Cycle: Processes, Human Impacts, and Strategies for...
"Understanding the Carbon Cycle: Processes, Human Impacts, and Strategies for..."Understanding the Carbon Cycle: Processes, Human Impacts, and Strategies for...
"Understanding the Carbon Cycle: Processes, Human Impacts, and Strategies for...
MMariSelvam4
 
Celebrating World-environment-day-2024.pdf
Celebrating  World-environment-day-2024.pdfCelebrating  World-environment-day-2024.pdf
Celebrating World-environment-day-2024.pdf
rohankumarsinghrore1
 
Navigating the complex landscape of AI governance
Navigating the complex landscape of AI governanceNavigating the complex landscape of AI governance
Navigating the complex landscape of AI governance
Piermenotti Mauro
 
Artificial Reefs by Kuddle Life Foundation - May 2024
Artificial Reefs by Kuddle Life Foundation - May 2024Artificial Reefs by Kuddle Life Foundation - May 2024
Artificial Reefs by Kuddle Life Foundation - May 2024
punit537210
 
Sustainable farming practices in India .pptx
Sustainable farming  practices in India .pptxSustainable farming  practices in India .pptx
Sustainable farming practices in India .pptx
chaitaliambole
 
Sustainable Rain water harvesting in india.ppt
Sustainable Rain water harvesting in india.pptSustainable Rain water harvesting in india.ppt
Sustainable Rain water harvesting in india.ppt
chaitaliambole
 
Presentación Giulio Quaggiotto-Diálogo improbable .pptx.pdf
Presentación Giulio Quaggiotto-Diálogo improbable .pptx.pdfPresentación Giulio Quaggiotto-Diálogo improbable .pptx.pdf
Presentación Giulio Quaggiotto-Diálogo improbable .pptx.pdf
Innovation and Technology for Development Centre
 
一比一原版(UMTC毕业证书)明尼苏达大学双城分校毕业证如何办理
一比一原版(UMTC毕业证书)明尼苏达大学双城分校毕业证如何办理一比一原版(UMTC毕业证书)明尼苏达大学双城分校毕业证如何办理
一比一原版(UMTC毕业证书)明尼苏达大学双城分校毕业证如何办理
zm9ajxup
 
Scope of political science habaushS.pptx
Scope of political science habaushS.pptxScope of political science habaushS.pptx
Scope of political science habaushS.pptx
Ni Ca
 
alhambra case study Islamic gardens part-2.pptx
alhambra case study Islamic gardens part-2.pptxalhambra case study Islamic gardens part-2.pptx
alhambra case study Islamic gardens part-2.pptx
CECOS University Peshawar, Pakistan
 
Q&A with the Experts: The Food Service Playbook
Q&A with the Experts: The Food Service PlaybookQ&A with the Experts: The Food Service Playbook
Q&A with the Experts: The Food Service Playbook
World Resources Institute (WRI)
 
Willie Nelson Net Worth: A Journey Through Music, Movies, and Business Ventures
Willie Nelson Net Worth: A Journey Through Music, Movies, and Business VenturesWillie Nelson Net Worth: A Journey Through Music, Movies, and Business Ventures
Willie Nelson Net Worth: A Journey Through Music, Movies, and Business Ventures
greendigital
 

Recently uploaded (20)

Climate Change All over the World .pptx
Climate Change All over the World  .pptxClimate Change All over the World  .pptx
Climate Change All over the World .pptx
 
International+e-Commerce+Platform-www.cfye-commerce.shop
International+e-Commerce+Platform-www.cfye-commerce.shopInternational+e-Commerce+Platform-www.cfye-commerce.shop
International+e-Commerce+Platform-www.cfye-commerce.shop
 
Characterization and the Kinetics of drying at the drying oven and with micro...
Characterization and the Kinetics of drying at the drying oven and with micro...Characterization and the Kinetics of drying at the drying oven and with micro...
Characterization and the Kinetics of drying at the drying oven and with micro...
 
Summary of the Climate and Energy Policy of Australia
Summary of the Climate and Energy Policy of AustraliaSummary of the Climate and Energy Policy of Australia
Summary of the Climate and Energy Policy of Australia
 
Alert-driven Community-based Forest monitoring: A case of the Peruvian Amazon
Alert-driven Community-based Forest monitoring: A case of the Peruvian AmazonAlert-driven Community-based Forest monitoring: A case of the Peruvian Amazon
Alert-driven Community-based Forest monitoring: A case of the Peruvian Amazon
 
Daan Park Hydrangea flower season I like it
Daan Park Hydrangea flower season I like itDaan Park Hydrangea flower season I like it
Daan Park Hydrangea flower season I like it
 
How about Huawei mobile phone-www.cfye-commerce.shop
How about Huawei mobile phone-www.cfye-commerce.shopHow about Huawei mobile phone-www.cfye-commerce.shop
How about Huawei mobile phone-www.cfye-commerce.shop
 
Prevalence of Toxoplasma gondii infection in domestic animals in District Ban...
Prevalence of Toxoplasma gondii infection in domestic animals in District Ban...Prevalence of Toxoplasma gondii infection in domestic animals in District Ban...
Prevalence of Toxoplasma gondii infection in domestic animals in District Ban...
 
"Understanding the Carbon Cycle: Processes, Human Impacts, and Strategies for...
"Understanding the Carbon Cycle: Processes, Human Impacts, and Strategies for..."Understanding the Carbon Cycle: Processes, Human Impacts, and Strategies for...
"Understanding the Carbon Cycle: Processes, Human Impacts, and Strategies for...
 
Celebrating World-environment-day-2024.pdf
Celebrating  World-environment-day-2024.pdfCelebrating  World-environment-day-2024.pdf
Celebrating World-environment-day-2024.pdf
 
Navigating the complex landscape of AI governance
Navigating the complex landscape of AI governanceNavigating the complex landscape of AI governance
Navigating the complex landscape of AI governance
 
Artificial Reefs by Kuddle Life Foundation - May 2024
Artificial Reefs by Kuddle Life Foundation - May 2024Artificial Reefs by Kuddle Life Foundation - May 2024
Artificial Reefs by Kuddle Life Foundation - May 2024
 
Sustainable farming practices in India .pptx
Sustainable farming  practices in India .pptxSustainable farming  practices in India .pptx
Sustainable farming practices in India .pptx
 
Sustainable Rain water harvesting in india.ppt
Sustainable Rain water harvesting in india.pptSustainable Rain water harvesting in india.ppt
Sustainable Rain water harvesting in india.ppt
 
Presentación Giulio Quaggiotto-Diálogo improbable .pptx.pdf
Presentación Giulio Quaggiotto-Diálogo improbable .pptx.pdfPresentación Giulio Quaggiotto-Diálogo improbable .pptx.pdf
Presentación Giulio Quaggiotto-Diálogo improbable .pptx.pdf
 
一比一原版(UMTC毕业证书)明尼苏达大学双城分校毕业证如何办理
一比一原版(UMTC毕业证书)明尼苏达大学双城分校毕业证如何办理一比一原版(UMTC毕业证书)明尼苏达大学双城分校毕业证如何办理
一比一原版(UMTC毕业证书)明尼苏达大学双城分校毕业证如何办理
 
Scope of political science habaushS.pptx
Scope of political science habaushS.pptxScope of political science habaushS.pptx
Scope of political science habaushS.pptx
 
alhambra case study Islamic gardens part-2.pptx
alhambra case study Islamic gardens part-2.pptxalhambra case study Islamic gardens part-2.pptx
alhambra case study Islamic gardens part-2.pptx
 
Q&A with the Experts: The Food Service Playbook
Q&A with the Experts: The Food Service PlaybookQ&A with the Experts: The Food Service Playbook
Q&A with the Experts: The Food Service Playbook
 
Willie Nelson Net Worth: A Journey Through Music, Movies, and Business Ventures
Willie Nelson Net Worth: A Journey Through Music, Movies, and Business VenturesWillie Nelson Net Worth: A Journey Through Music, Movies, and Business Ventures
Willie Nelson Net Worth: A Journey Through Music, Movies, and Business Ventures
 

Presentation 20220316 nandia

  • 1. 1 Student: Geserbaatar Nandin-erdene Supervisor: Prof. Kenlo Nishida Nasahara 16th March, 2022 Estimation of the Above-ground Biomass and Carbon Stock in Boreal Forest Using Satellite Data with Machine Learning
  • 2. Outline 1. Introduction 2. Research objectives 3. Materials and methods 4. Data analysis and results 5. Conclusion 2
  • 3. 1. Introduction 3 Source: National Forest Inventory of Mongolia & Forest loss (Hansen et al., 2013 ) Boreal forest covers about 9.2% of the total area of Mongolia. But those forests are decreasing. 2020 2001
  • 4. Forest area (1000 ha) Growing stock (million m3 ) 1990 14352.0 1382.2 2000 14263.9 1373.3 2010 14183.9 1365.4 2015 14178.3 1365.3 2020 14172.7 1364.6 Source: Global forest resources assessment 2020 4 Table 1. Boreal forest area change 1990 - 2020 Both area and stock of forests have been declining for the past 30 years! Decreasing! Decreasing! 1.1 Introduction (cont’d)
  • 5. 5 Forest loss is mostly due to fire and insects!! 1.2 Introduction (cont’d) Forest loss Forest fire and insect damages
  • 6. 1.3 Introduction (cont’d) 6 Current situation of forest data in Mongolia --- Have to be updated every 5 years in all forested area --- Use field measurement and allometric equation --- Spend more time, challenging to reach some area, and costly
  • 7. 2. Research objectives Main objective: To map forest above-ground biomass and carbon stock using satellite data with machine learning Goals: ➢ To develop a suitable model ➢ To estimate forest above-ground biomass (AGB) ➢ To evaluate boreal forest carbon stock 7
  • 8. 8 3. Materials and Methods 3.1 Study area 3.2 Field data 3.3 Satellite data 3.4 Methodology
  • 9. 3.1 Study area 9 Location: Latitude: 47°N - 53°N, Longitude: 96° E - 104°E Climate: Average annual rainfall 270 mm, and annual mean temperature around 1.3 °C Climate classification: Dwc (continental, dry winter, cold summer) Total area: 20466182 ha Forested area: 9380532 ha (45.8%) Source: Environmental information center (www.eic.mn )
  • 10. 10 3.2 Field data The distribution of field data Plot arrangement Total field plots in study area = 5720 AGB (Mg/ha) 1 - 50 50 - 100 100 - 150 150 - 200 200 - 250 Number of plot 1952 2570 1017 170 11 Average AGB (Mg/ha) 69.7 Number of plots r = 6m DBH 6 cm - 14.9 cm r = 12m DBH 15 cm - 29.9 cm r = 20m DBH ≥ 30 cm Note: Diameter breast height (DBH) Source: Multi-purpose national forest inventory, Forest Resource Development Center
  • 11. 3.3 Satellite data 11 Satellite name Part / Row Time Landsat 8 OLI p133r25, p133r27 p133r26 p134r25, p134r26, p134r27 p135r24, p135r25, p135r26, p135r27 p136r24, p136r25, p136r26, p136r27 p137r24 p137r25 p137r26 p138r25, p138r26 2014 September 10 2013 September 7 2014 September 1 2013 September 5 2019 August 28 2017 August 29 2020 September 6 2015 July 23 2018 September 8 ALOS-2 / PALSAR 2 N47E100, 101, 102 N48E098, 099, 100, 101, 102, 103, 104 N49E098, 099, 100, 101, 102, 103, 104 N50E096, 097, 098, 099,100, 101, 102, 103, 104 N51E097, 098, 099, 100, 101, 102, 103, 104 N52E097, 098, 099, 100, 101, 102 N53E098, 099 2015 Table 2. Collected satellites data
  • 13. 13 4. Data analysis and results 4.1 Input features for machine learning (ML) 4.2 Accuracy of forest above-ground biomass (AGB) prediction 4.3 Hyperparameter values of ML algorithms 4.4 Feature importance for random forest (RF) 4.5 Predicted map derived from RF model 4.6 Reference data errors
  • 14. 14 4.1 Input features for machine learning (ML) Landsat 8 OLI B2 - blue band B3 - green band B4 - red band B5 - NIR B6 - SWIR1 B7 - SWIR2 Normalised difference vegetation index (NDVI) NDVI = (NIR - red) / (NIR + red) Normalised difference water index (NDWI) NDWI = (NIR - SWIR 1) / (NIR + SWIR 1) Green leaf index (GLI) GLI = (2 * green - red - blue) / (2 * green + red + blue) Enhanced vegetation index (EVI) EVI = 2.5 * (NIR - red) / (NIR + 6 * red - 7.5 * blue + 1) Enhanced vegetation index 2 (EVI2) EVI2 = 2.5 * (NIR - red) / (NIR + 2.4 * red + 1) Soil adjusted vegetation index (SAVI) SAVI = ((NIR - red) / (NIR + red + 0.5)) * 1.5 Ratio vegetation index (RVI) RVI = NIR / red Difference vegetation index (DVI) DVI = NIR - red Green normalised vegetation index (GNDVI) GNDVI = (NIR - green) / (NIR + green) ALOS-2 / PALSAR 2 HH polarization HV polarization Ratio HH and HV (HH/HV) Ratio HV and HH (HV/HH) Difference HH and HV (HH - HV) Radar forest degradation index (RFDI) RFDI = (HH - HV) / (HH + HV) Topographic data Digital Elevation Model (DEM), Slope, Aspect Table 3. Input features
  • 15. 15 4.2 Accuracy of forest above-ground biomass (AGB) prediction RF (Random Forest) XGB (Extreme Gradient Boost) SVR (Support Vector Regression) Landsat 8 OLI ALOS-2 / PALSAR-2 Landsat 8 OLI & ALOS-2 / PALSAR-2 Predicted AGB (Mg/ha) Observed AGB (Mg/ha) R2 : 0.235 RMSE : 33 Mg/ha R2 : 0.106 RMSE : 36 Mg/ha R2 : 0.24 RMSE : 33 Mg/ha R2 : 0.234 RMSE : 33 Mg/ha R2 : 0.085 RMSE : 37 Mg/ha R2 : 0.24 RMSE : 33 Mg/ha R2 : 0.204 RMSE : 34 Mg/ha R2 : 0.072 RMSE : 37 Mg/ha R2 : 0.194 RMSE : 34 Mg/ha
  • 16. 16 4.2 Accuracy of forest above-ground biomass (AGB) prediction (cont’d) LR (Linear Regression) AdaBoost DT (Decision Tree) KNN (k-Nearest Neighbor) Landsat 8 OLI ALOS-2 / PALSAR-2 Landsat 8 OLI & ALOS-2 / PALSAR-2 Predicted AGB (Mg/ha) Observed AGB (Mg/ha) R2 : 0.195 RMSE : 34 Mg/ha R2 : 0.01 RMSE : 38 Mg/ha R2 : 0.151 RMSE : 35 Mg/ha R2 : 0.171 RMSE : 35 Mg/ha R2 : 0.096 RMSE : 36 Mg/ha R2 : 0.187 RMSE : 34 Mg/ha R2 : 0.149 RMSE : 35 Mg/ha R2 : 0.075 RMSE : 37 Mg/ha R2 : 0.162 RMSE : 35 Mg/ha R2 : 0.204 RMSE : 34 Mg/ha R2 : 0.075 RMSE : 37 Mg/ha R2 : 0.20 RMSE : 34 Mg/ha
  • 17. 17 4.3 Hyperparameter values of ML algorithms Algorithm learning _rate max_ depth min_samples_leaf / min_child_weight n_estimators / C value kernel gamma R2 (training) R2 (testing) RMSE Mg/ha LR (Linear Regression) NA NA NA NA NA NA 0.210 0.151 35 XGB (Extreme Gradient Boost ) 0.1 5 2 100 NA 1 0.578 0.24 33 AdaBoost 0.01 NA NA 100 NA NA 0.211 0.187 34 DT (Decision Tree ) NA 4 30 NA NA NA 0.211 0.162 35 RF (Random Forest) NA 20 10 1000 NA NA 0.570 0.24 33 KNN (k-Nearest Neighbor) n_neighbor = 25, metric = ‘minkowski’, p = 2 0.244 0.20 34 SVR (Support Vector Regression) NA NA NA 500 rbf NA 0.231 0.194 34 Table 4. Configured hyperparameters for each ML
  • 18. 18 4.4 Feature importance for random forest (RF) model High importance: SWIR1 (Short-wave infrared band 1 of Landsat 8) GLI (Green leaf index) HV (Horizontal transmitting, vertical receiving polarization of ALOS-2 ) DEM (Digital elevation model)
  • 19. 19 4.5 Predicted map derived from RF model Forest above-ground biomass Forest carbon stock
  • 20. 20 4.6 Reference data errors 1. High AGB value on the sparse forest 2. Low AGB value on the dense forest 3. Plot covered by forest and non forest area Notes: yellow number is AGB value, unit is Mg/ha, and yellow circle’s radius is 30 m. 1 2 3 Total 812 plots Source: Bing aerial map & Google map
  • 21. 21 5. Conclusion * Hyperparameter values were effectively influenced by overfitting error. * SVR, KNN, and LR models were high R2 in only using Landsat data. * The best regression model was RF. The coefficient of determination (R2 ) was 0.24 and RMSE was 33 Mg/ha. Forest AGB was estimated 32.5 Mg/ha - 122.5 Mg/ha and forest carbon stock was estimated 16.5 Mg C/ha - 62.5 Mg C/ha. * The highest importance variables were SWIR1, GLI, HV and DEM for the RF model. * After data screening, 812 plots of reference data were errors. From data screening analysis and my research, forest AGB data of National Forest Inventory in Mongolia was bad quality. * In the future, reference field data need validation and update.
  • 22. 22 References Dan, A. (2019). Multipurpose national forest inventory in Mongolia, 2014-2017-A tool to support sustainable forest management. Geography, Environment, Sustainability, 12(3), 167-183. Environmental information center. (2020). http://www.eic.mn FAO. (2020). Global forest resources assessment 2020. FAO. http://www.fao.org/3/cb0031en/cb0031en.pdf Hansen, M. C., P. V. Potapov, R. Moore, M. Hancher, S. A. Turubanova, A. Tyukavina, D. Thau, S. V. Stehman, S. J. Goetz, T. R. Loveland, A. Kommareddy, A. Egorov, L. Chini, C. O. Justice, and J. R. G. Townshend. 2013. “High-Resolution Global Maps of 21st-Century Forest Cover Change.” Science 342 (15 November): 850–53. Data available online from: http://earthenginepartners.appspot.com/science-2013-global-forest. FRDC. (2017). Multi-purpose national forest inventory in Mongolia Nachin, B., & Sukhbaatar, G. (2013). Some results of forest carbon stock calculation in northern Mongolia. UNREDD. www.unredd.net
  • 23. Thank you for your attention! 23