GEE环境下的玉米低温冷害损失快速评估

大范围、及时、准确的灾害损失评估与制图对防灾减灾、农业保险和粮食安全等至关重要。针对传统灾害损失评估方法空间尺度单一、泛化能力差、时效性低，可操作性弱等问题，本文建立了一种遥感产品耦合作物模型的多尺度的灾害损失评估方法MDLA （a Multiscale Disaster Loss Assessment）。该方法利用作物模型的多情景模拟产生大量的灾害样本，结合对应日期的遥感指标构建灾害脆弱性模型，依托Google Earth Engine（GEE）平台将其应用到高分辨率遥感影像和格点灾害指标进行逐象元评估。以鄂伦春自治旗玉米为例，基于精细校准的CERES-Maize模型的模拟，利用两个生长季窗口的LAI和冷积温（CDD）建立统计模型来刻画低温对最终产量的影响，结合Sentinel-2数据逐格点计算完成高精度损失制图。结果显示，校准后的CERES-Maize模拟物候和产量的NRMSE 分别为3.3%和8.9%。冷害情景模拟结果表明不同类型和生育期的低温冷害对玉米产量的影响不尽相同，其中生长峰值期（出苗—吐丝和吐丝—灌浆）最为敏感。回代检验显示，MDLA方法估算精度为11.4%，与历史冷害年份的实际损失相吻合。经评估，鄂伦春2018-08-09的冷害导致玉米减产23.7%，受灾面积1.86×10⁴ ha，其中高海拔地区损失较重（减产率>25%），低温冷害对该区玉米生产构成了严重的威胁。与现有的统计回归、作物模型模拟以及同化等技术相比，其优势在于：（1）结合遥感观测和作物模型模拟技术能更好地刻画了灾害对产量的影响过程；（2）利用GEE平台快速处理海量遥感数据，提高了灾害损失评估的时效性；（3）不受地面实测数据的限制，易操作，可实现动态、多尺度（象元、田块、村，县等）的损失评估，这为防灾减损、维持粮食丰产稳产提供了保障，也为农业保险的业务化运行提供了思路。     

Farm-Level Yield mapping for precision crop management by linking remote sensing inputs and a crop simulation model

A study aimed at generating wheat yield maps of farmer’s fields by using remote sensing (RS) inputs was undertaken during the rabi season of 1998-99 in six villages of Alipur Block of Delhi State. RS derived leaf area index (LAI) were linked to wheat simulation model WTGROWS by adopting a strategy christened “Modified Corrective Approach”. This essentially uses an empirical relation of grain yield and LAI, which was derived from WTGROWS simulation model by running model for a combination of input resources, management practices and soil types occurring in the area. This biometric relationship was applied to all the wheat fields of the study area for which the LAI was derived from single acquisition of IRS LISS-III data (Jan 27, 99). The LAI-NDVI relation adopted was logarithmic in nature (R²=0.83) and was based on ground measurements of LAI in farmer’s fields in the same area. A comparison of predicted grain yield by the modified corrective approach and actual observed yield for the 22 farmer’s fields showed high correlation coefficient of 0.8 and a root mean square error (RMSE) of 597 kg ha^-1 which was 17% of the observed mean yield. Thus linking of RS information and crop simulation model provides an alternative for mapping and forecasting crop yield under highly variable cropping environment of Indian farms, which is a pre-requisite for implementing Precision Crop Management (PCM).     

Predicting Wheat Grain and Biomass Yield Using Canopy Reflectance of Booting Stage

Field experiment was conducted in a sandy loam soil of Indian Agricultural Research Institute, New Delhi during the year 2011–13 to see the effect of irrigation, mulch and nitrogen on canopy spectral reflectance indices and their use in predicting the grain and biomass yield of wheat. The canopy reflectances were measured using a hand held ASD FieldSpec Spectroradiometer at booting stage of wheat. Four spectral reflectance indices (SRIs) viz. RNDVI (Red Normalized Difference Vegetation Index), GNDVI (Green Normalized Difference Vegetation Index), SR (Simple Ratio) and WI (Water Index) were computed using the spectral reflectance data. Out of these four indices, RNDVI, GNDVI and SR were significantly and positively related with the grain and biomass yield of wheat whereas WI was significantly and negatively related with the grain and biomass yield of wheat. Calibration with the second year data showed that among the SRIs, WI could account for respectively, 85 % and 86 % variation in grain and biomass yield of wheat with least RMSE (395 kg ha^?1 (15 %) for grain yield and 1609 kg ha^?1 (20 %) for biomass yield) and highest d index (0.95 for grain yield and 0.91 for biomass yield). Therefore it can be concluded that WI measured at booting stage can be successfully used for prediction of grain and biomass yield of wheat.     

Regional yield estimation for winter wheat with MODIS-NDVI data in Shandong, China

The significance of crop yield estimation is well known in agricultural management and policy development at regional and national levels. The primary objective of this study was to test the suitability of the method, depending on predicted crop production, to estimate crop yield with a MODIS-NDVI-based model on a regional scale. In this paper, MODIS-NDVI data, with a 250 m resolution, was used to estimate the winter wheat (Triticum aestivum L.) yield in one of the main winter-wheat-growing regions. Our study region is located in Jining, Shandong Province. In order to improve the quality of remote sensing data and the accuracy of yield prediction, especially to eliminate the cloud-contaminated data and abnormal data in the MODIS-NDVI series, the Savitzky–Golay filter was applied to smooth the 10-day NDVI data. The spatial accumulation of NDVI at the county level was used to test its relationship with winter wheat production in the study area. A linear regressive relationship between the spatial accumulation of NDVI and the production of winter wheat was established using a stepwise regression method. The average yield was derived from predicted production divided by the growing acreage of winter wheat on a county level. Finally, the results were validated by the ground survey data, and the errors were compared with the errors of agro-climate models. The results showed that the relative errors of the predicted yield using MODIS-NDVI are between −4.62% and 5.40% and that whole RMSE was 214.16 kg ha⁻¹ lower than the RMSE (233.35 kg ha⁻¹) of agro-climate models in this study region. A good predicted yield data of winter wheat could be got about 40 days ahead of harvest time, i.e. at the booting-heading stage of winter wheat. The method suggested in this paper was good for predicting regional winter wheat production and yield estimation.     

Monitoring canopy growth and grain yield of paddy rice in South Korea by using the GRAMI model and high spatial resolution imagery

Monitoring crop conditions and forecasting crop yields are both important for assessing crop production and for determining appropriate agricultural management practices; however, remote sensing is limited by the resolution, timing, and coverage of satellite images, and crop modeling is limited in its application at regional scales. To resolve these issues, the Gramineae (GRAMI)-rice model, which utilizes remote sensing data, was used in an effort to combine the complementary techniques of remote sensing and crop modeling. The model was then investigated for its capability to monitor canopy growth and estimate the grain yield of rice (Oryza sativa), at both the field and the regional scales, by using remote sensing images with high spatial resolution. The field scale investigation was performed using unmanned aerial vehicle (UAV) images, and the regional-scale investigation was performed using RapidEye satellite images. Simulated grain yields at the field scale were not significantly different (p = 0.45, p = 0.27, and p = 0.52) from the corresponding measured grain yields according to paired t-tests (α = 0.05). The model’s projections of grain yield at the regional scale represented the spatial grain yield variation of the corresponding field conditions to within ±1 standard deviation. Therefore, based on mapping the growth and grain yield of rice at both field and regional scales of interest within coverages of a UAV or the RapidEye satellite, our results demonstrate the applicability of the GRAMI-rice model to the monitoring and prediction of rice growth and grain yield at different spatial scales. In addition, the GRAMI-rice model is capable of reproducing seasonal variations in rice growth and grain yield at different spatial scales.     

Winter wheat yield forecasting in Ukraine based on Earth observation,meteorological data and biophysical models

Ukraine is one of the most developed agriculture countries and one of the biggest crop producers in the world. Timely and accurate crop yield forecasts for Ukraine at regional level become a key element in providing support to policy makers in food security. In this paper, feasibility and relative efficiency of using moderate resolution satellite data to winter wheat forecasting in Ukraine at oblast level is assessed. Oblast is a sub-national administrative unit that corresponds to the NUTS2 level of the Nomenclature of Territorial Units for Statistics (NUTS) of the European Union. NDVI values were derived from the MODIS sensor at the 250 m spatial resolution. For each oblast NDVI values were averaged for a cropland map (Rainfed croplands class) derived from the ESA GlobCover map, and were used as predictors in the regression models. Using a leave-one-out cross-validation procedure, the best time for making reliable yield forecasts in terms of root mean square error was identified. For most oblasts, NDVI values taken in April–May provided the minimum RMSE value when comparing to the official statistics, thus enabling forecasts 2–3 months prior to harvest. The NDVI-based approach was compared to the following approaches: empirical model based on meteorological observations (with forecasts in April–May that provide minimum RMSE value) and WOFOST crop growth simulation model implemented in the CGMS system (with forecasts in June that provide minimum RMSE value). All three approaches were run to produce winter wheat yield forecasts for independent datasets for 2010 and 2011, i.e. on data that were not used within model calibration process. The most accurate predictions for 2010 were achieved using the CGMS system with the RMSE value of 0.3 t ha⁻¹ in June and 0.4 t ha⁻¹ in April, while performance of three approaches for 2011 was almost the same (0.5–0.6 t ha⁻¹ in April). Both NDVI-based approach and CGMS system overestimated winter wheat yield comparing to official statistics in 2010, and underestimated it in 2011. Therefore, we can conclude that performance of empirical NDVI-based regression model was similar to meteorological and CGMS models when producing winter wheat yield forecasts at oblast level in Ukraine 2–3 months prior to harvest, while providing minimum requirements to input datasets.     

Inter-comparison of remote sensing platforms for height estimation of mango and avocado tree crowns

To support the adoption of precision agricultural practices in horticultural tree crops, prior research has investigated the relationship between crop vigour (height, canopy density, health) as measured by remote sensing technologies, to fruit quality, yield and pruning requirements. However, few studies have compared the accuracy of different remote sensing technologies for the estimation of tree height. In this study, we evaluated the accuracy, flexibility, aerial coverage and limitations of five techniques to measure the height of two types of horticultural tree crops, mango and avocado trees. Canopy height estimates from Terrestrial Laser Scanning (TLS) were used as a reference dataset against height estimates from Airborne Laser Scanning (ALS) data, WorldView-3 (WV-3) stereo imagery, Unmanned Aerial Vehicle (UAV) based RGB and multi-spectral imagery, and field measurements. Overall, imagery obtained from the UAV platform were found to provide tree height measurement comparable to that from the TLS (R² = 0.89, RMSE = 0.19 m and rRMSE = 5.37 % for mango trees; R² = 0.81, RMSE = 0.42 m and rRMSE = 4.75 % for avocado trees), although coverage area is limited to 1–10 km² due to battery life and line-of-sight flight regulations. The ALS data also achieved reasonable accuracy for both mango and avocado trees (R² = 0.67, RMSE = 0.24 m and rRMSE = 7.39 % for mango trees; R² = 0.63, RMSE = 0.43 m and rRMSE = 5.04 % for avocado trees), providing both optimal point density and flight altitude, and therefore offers an effective platform for large areas (10 km²–100 km²). However, cost and availability of ALS data is a consideration. WV-3 stereo imagery produced the lowest accuracies for both tree crops (R² = 0.50, RMSE = 0.84 m and rRMSE = 32.64 % for mango trees; R² = 0.45, RMSE = 0.74 m and rRMSE = 8.51 % for avocado trees) when compared to other remote sensing platforms, but may still present a viable option due to cost and commercial availability when large area coverage is required. This research provides industries and growers with valuable information on how to select the most appropriate approach and the optimal parameters for each remote sensing platform to assess canopy height for mango and avocado trees.     

Evaluation of machine learning models for rice dry biomass estimation and mapping using quad-source optical imagery

ABSTRACT

Several machine learning regression models have been advanced for the estimation of crop biophysical parameters with optical satellite imagery. However, literature on the comparative performances of such models is still limited in range and scope, especially under multiple data sources, despite the potential of multi-source imagery to improving crop monitoring in cloudy areas. To fill in this knowledge gap, this study explored the synergistic use of Landsat-8, Sentinel-2A, China’s environment and disaster monitoring and forecasting satellites (HJ-1 A and B) and Gaofen-1 (GF-1) data to evaluate four machine learning regression models that include Random Forest (RF), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), and Gradient Boosting Decision Tree (GBDT), for rice dry biomass estimation and mapping. Taking a major rice cultivation area in southeast China as case study during the 2016 and 2017 growing seasons, a cross-calibrated time series of the Enhanced Vegetation Index (EVI) was obtained from the quad-source optical imagery and on which the aforementioned models were applied, respectively. Results indicate that in the before rice heading scenario, the most accurate dry biomass estimates were obtained by the GBDT model (R² of 0.82 and RMSE of 191.8 g/m²) followed by the RF model (R² of 0.79 and RMSE of 197.8 g/m²). After heading, the k-NN model performed best (R² of 0.43 and RMSE of 452.1 g/m²) followed by the RF model (R² of 0.42 and RMSE of 464.7 g/m²). Whist the k-NN model performed least in the before heading scenario, SVM performed least in the after heading scenario. These findings may suggest that machine learning regression models based on an ensemble of decision trees (RF and GBDT) are more suitable for the estimation of rice dry biomass, at least with optical satellite imagery. Studies that would extend the evaluation of these machine learning models, to other parameters like leaf area index, and to microwave imagery, are hereby recommended.     

构建地块二维表征及CNN模型的作物遥感分类

本文旨在研究基于地块数据约束的深度学习模型的分类特征表示方法,以识别不同作物在不同时相上光谱差异从而对作物类型进行分类。通过Google Earth Engine平台获取作物生育期内全部Landsat 8影像,利用其质量评定波段完成研究区无云时相及区域上的地块统计,提取地块级别的各波段反射率均值按照时相顺序及波长进行排列,构建波谱、时相二维特征图作为该地块的抽象表示。通过构建相对最优的卷积神经网络CNN（Convolutional Neural Network）结构完成对特征图的分类,从而完成对地块的分类。构建CNN模型并不需要手工特征和预定义功能的需求,可完成提取特征并遵循端到端原则进行分类。将该模型的分类结果与其他最为常用机器学习分类器进行了比较,获得了优于常用遥感分类算法的分类精度。结果表明地块数据的加入可以有效的缩减计算规模并提供了准确的分类边界。所提出得方法在地块特征表示及作物分类中具有突出的应用潜力,应视为基于地块的多时相影像分类任务的优选方法。     

应用粒子群算法的遥感信息与水稻生长模型同化技术

在研究遥感信息和水稻生长模型的同化过程中, 最小化遥感反演与生长模型(RiceGrow)输出的水稻生长 信息差值绝对值时引入了一种新的优化算法-粒子群算法(PSO), 并对比了其与模拟退火算法(SA)的优缺点; 探讨 了叶面积指数(LAI)和叶片氮积累量(LNA)分别作为同化参数时的同化效果。结果表明, PSO 无论是从同化效率还是 反演精度上都要好于SA, 粒子群优化算法是一种可靠的遥感与模型同化算法; LAI 和LNA 作为外部同化参数时各 有优势, LAI 作为同化参数可获得较准确的播期及播种量, 而LNA 作为同化参数可获得更为准确的施氮量信息。但 是LAI 作为外部同化参数时的反演结果总体要优于利用LNA 作为同化参数时的反演结果。利用试验资料对该技术 进行了测试和检验, 结果显示反演的模型初始参数的平均值与真实值的相对误差(RE)均小于2.5%, 均方根误差 (RMSE)为0.7—2.2, 产量模拟值与实测值之间的相对误差为5%左右, 模拟与实测相关指标值吻合度较高, 该同化 技术具有较好的适用性。从而为生长模型从单点扩展到区域尺度应用奠定了基础。     

MODIS植被指数的美国玉米单产遥感估测

针对中国开展的国外农作物产量遥感估测大多依靠中低分辨率耕地信息、省级(州级)或国家级作物产量统计数据的现状,本文以美国玉米为例,探讨利用多年中高分辨率作物分布信息、时序遥感植被指数和县级作物产量统计数据开展国外重点地区作物单产遥感估测技术研究,以期进一步提高中国对国外农作物产量监测精度和精细化水平。首先,利用美国农业部国家农业统计局(NASS/USDA)生产的作物分布数据(CDL)获得多个年份玉米空间分布图,并对相应年份250 m分辨率16天合成的MODIS-NDVI时序数据进行掩膜处理,统计获得每年各县域内玉米主要生育期NDVI均值;其次,以各州为估产区,以多年县级玉米统计单产和县域内玉米主要生育期NDVI均值为基础,建立各州玉米主要生育期NDVI与玉米单产间关系模型;然后,通过主要生育期玉米单产和玉米植被指数间拟合程度,筛选确定各州玉米最佳估产期和最佳估产模型。最终,利用最佳估产模型实现美国各州玉米单产估测和全国玉米单产推算。其中,建模数据覆盖时间为2007年—2010年,验证数据为2011年。结果表明,应用最佳估产模型的2011年美国各州玉米单产估测相对误差在-4.16%—4.92%,均方根误差在148.75—820.93 kg/ha,各州估测结果计算获得全国玉米单产的相对误差仅为2.12%,均方根误差为285.57 kg/ha。可见,本研究的作物单产遥感估测技术方法具有一定可行性,可准确估测全球重点地区作物单产信息。     

Wheat crop production estimation using satellite data

This paper reports acreage, yield and production forecasting of wheat crop using remote sensing and agrometeorological data for the 1998–99 rabi season. Wheat crop identification and discrimination using Indian Remote Sensing (IRS) ID LISS III satellite data was carried out by supervised maximum likelihood classification. Three types of wheat crop viz. wheat-1 (high vigour-normal sown), wheat-2 (moderate vigour-late sown) and wheat-3 (low vigour-very late sown) have been identified and discriminated from each other. Before final classification of satellite data spectral separability between classes were evaluated. For yield prediction of wheat crop spectral vegetation indices (RVI and NDVI), agrometeorological parameters (ET_max and TD) and historical crop yield (actual yield) trend analysis based linear and multiple linear regression models were developed. The estimated wheat crop area was 75928.0 ha. for the year 1998–99, which sowed ?2.59% underestimation with land record commissioners estimates. The yield prediction through vegetation index based and vegetation index with agrometeorological indices based models were 1753 kg/ha and 1754 kg/ha, respectively and have shown relative deviation of 0.17% and 0.22%, the production estimates from above models when compared with observed production show relative deviation of ?2.4% and ?2.3% underestimations, respectively.     

基于双频多极化数据的农作物后向散射特性模拟分析及类型识别

以北京昌平地区为研究区域,获取了2007年该试验区C波段ENVISAT/ASAR数据和L波段ALOS/PALSAR数据,并提取了地物的后向散射系数。首先,利用MIMICS模型对该地区的春玉米、夏玉米和果木的后向散射特性进行模拟和分析;然后,将模拟结果同雷达实际观测数据进行对比;最后,利用不同作物之间的后向散射系数数值大小关系,建立分类二叉树,很好地区分了春玉米和夏玉米,总分类精度达86.66%。研究结果表明:双频多极化雷达数据能够提供有利于作物类型识别的多方面信息,对农作物遥感具有较大的优势和潜力。     

Integration of maximum crop response with machine learning regression model to timely estimate crop yield

Timely and reliable estimation of regional crop yield is a vital component of food security assessment, especially in developing regions. The traditional crop forecasting methods need ample time and labor to collect and process field data to release official yield reports. Satellite remote sensing data is considered a cost-effective and accurate way of predicting crop yield at pixel-level. In this study, maximum Enhanced Vegetation Index (EVI) during the crop-growing season was integrated with Machine Learning Regression (MLR) models to estimate wheat and rice yields in Pakistan's Punjab province. Five MLR models were compared using a fivefold cross-validation method for their predictive accuracy. The study results revealed that the regression model based on the Gaussian process outperformed over other models. The best performing model attained coefficient of determination (R2), Root Mean Square Error (RMSE, t/ ha), and Mean Absolute Error (MAE, t/ha) of 0.75, 0.281, and 0.236 for wheat; 0.68, 0.112, and 0.091 for rice, respectively. The proposed method made it feasible to predict wheat and rice 6– 8 weeks before the harvest. The early prediction of crop yield and its spatial distribution in the region can help formulate efficient agricultural policies for sustainable social, environmental, and economic progress.     

面向对象与卷积神经网络模型的GF-6 WFV影像作物分类

GF-6 WFV影像是中国首颗带有红边波段的中高分辨率8波段多光谱卫星的遥感影像,对于其影像及红边波段对作物分类影响的研究利用亟待展开。本文结合面向对象和深度学习提出一种适用于GF-6 WFV红边波段的卷积神经网络(RE-CNN)遥感影像作物分类方法。首先采用多尺度分割和ESP工具选择最佳分割参数完成影像分割,通过面向对象的CART决策树消除椒盐现象的同时提取植被区域,并转化为卷积神经网络的输入数据,最后基于Python和Numpy库构建的卷积神经网络模型(RE-CNN)用于影像作物分类及精度验证。有无红边波段的两组分类实验结果表明:在红边波段组,卷积神经网络(RE-CNN)作物分类识别取得了较好的效果,总体精度高达94.38%,相比无红边波段组分类精度提高了2.83%,验证了GF-6 WFV红边波段对作物分类的有效性。为GF-6 WFV红边波段影像用于作物的分类研究提供技术参考和借鉴价值。     

基于GF-1号影像的南方水稻种植信息提取

针对南方复杂地区水稻遥感信息提取研究中机器自动学习分类研究较少、分类精度不高的问题,以福建省三明市建宁县溪口镇为研究区,基于GF-1号卫星影像,采用面向对象的随机森林遥感分类算法对研究区内水稻田信息进行提取。首先通过优化面向对象分割参数和随机森林分类模型参数,提取并调用了影像中的多种特征;再对光谱特征、植被指数特征、纹理特征、几何特征进行特征空间优选;最后通过设置4种特征优选试验进行对比,得到最优分类模型。实验结果显示,基于特征空间优选的面向对象随机森林分类算法的水稻提取精度高达90%,分类总体精度可达87%,Kappa系数为0.85;与其他试验结果相比,漏分和误分现象较少,实现了南方地区水稻信息高精度自动识别。该方法计算特征少、实现简便,对于国产高分卫星影像在南方复杂地区作物自动提取中的应用具有参考性。     

Deducing Rice Crop Dynamics and Cultural Types of Bangladesh Using Geospatial Techniques

Rice crop occupies an important aspect of food security and also contributes to global warming via GHGs emission. Characterizing rice crop using spatial technologies holds the key for addressing issues of global warming and food security as different rice ecosystems respond differently to the changed climatic conditions. Remote sensing has become an important tool for assessing seasonal vegetation dynamics at regional and global scale. Bangladesh is one of the major rice growing countries in South Asia. In present study we have used remote sensing data along with GIS and ancillary map inputs in combination to derive seasonal rice maps, rice phenology and rice cultural types of Bangladesh. The SPOT VGT S10 NDVI data spanning Aus, Aman and Boro crop season (1^st May 2008 to 30^th April 2009) were used, first for generating the non-agriculture mask through ISODATA clustering and then to generate seasonal rice maps during second classification. The spectral rice profiles were modelled and phenological parameters were derived. NDVI growth profiles were modelled and crop calendar was derived. To segregate the rice cultural types of Bangladesh into IPCC rice categories, we used elevation, irrigated area, interpolated rainfall maps and flood map through logical modelling in GIS. The results indicated that the remote sensing derived rice area was 9.99 million ha as against the reported area of 11.28 million ha. The wet and dry seasons accounted for 64% and 36 % of the rice area, respectively. The flood prone, drought prone and deep water categories account for 7.5%, 5.56% and 2.03%, respectively. The novelty of current findings lies in the spatial outcome in form of seasonal and rice cultural type maps of Bangladesh which are helpful for variety of applications.     

General Regression Neural Network and Radial Basis Neural Network for the Estimation of Crop Variables of Lady Finger

Estimation of crop variables is necessary for crop type monitoring as well as crop yield forecast. At the present era artificial neural network methodology are widely used to the remote sensing domain for numerous applications like crop yield forecasting and crop type classification. In the present work, two neural network models namely general regression neural network (GRNN) and radial basis function neural network (RBFNN) are used to estimate crop variables: leaf area index (LAI), biomass (BM), plant height (PH) and soil moisture (SM) by using ground based X-band scatterometer data. The both networks are trained and tested with X-band scatterometer data. The performance of the GRNN and RBFNN networks are found that the radial basis approach is more suitable for crop variable estimation in comparison to the GRNN approach. This work presents the applicability of neural network as an estimator and method employed could be useful to estimate the crop variables of other crops.     

Modeling and mapping aboveground biomass of the restored mangroves using ALOS-2 PALSAR-2 in East Kalimantan,Indonesia

Accurate estimation of forest aboveground biomass (AGB) using remote sensing is a requisite for monitoring, reporting and verification (MRV) system of the United Nations Programme on Reducing Emissions from Deforestation and Forest Degradation. However, attaining high accuracy remains a great challenge in the diverse tropical forests. Among available technologies, l-band Synthetic Aperture Radar (SAR) estimates AGB with reasonably high accuracy in the terrestrial tropical forests. Nevertheless, the accuracy is relatively low in the mangrove forests. In this context, the study was carried out to model and map AGB using backscatter coefficients of Advanced Land Observing Satellite-2 (ALOS-2) Phased Array l-band SAR-2 (PALSAR-2) in part of the restored mangrove forest at Mahakam Delta, Indonesia. PALSAR-2 data was acquired with image scene observation during the peak low tide on 30 July 2018 from Japan Aerospace Exploration Agency. The forest parameters namely tree height and diameter at breast height were measured from 71 field plots in September-October 2018. The parameters were used in mangrove allometry to calculate the field AGB. Finally, HV polarized backscatter coefficients of PALSAR-2 were used to model AGB using linear regression. The model demonstrated a comparatively high performance using three distinct methods viz. independent validation (R² of 0.89 and RMSE of 23.16 tons ha⁻¹), random k-fold cross validation (R² of 0.89 and RMSE of 24.59 tons ha⁻¹) and leave location out cross validation (LLO CV) (R² of 0.88 and RMSE of 24.05 tons ha⁻¹). The high accuracy of the LLO CV indicates no spatial overfitting in the model. Thus, the model based on LLO CV was used to map AGB in the study area. This is the first study that successfully obtains high accuracy in modeling AGB in the mangrove forest. Therefore, it offers a significant contribution to the MRV mechanism for monitoring mangrove forests in the tropics and sub-tropics.