Large-area rice yield forecasting using satellite imageries

Ability to make large-area yield prediction before harvest is important in many aspects of agricultural decision-making. In this study, canopy reflectance band ratios (NIR/RED, NIR/GRN) of paddy rice (Oryza sativa L.) at booting stage, from field measurements conducted from 1999 to 2005, were correlated with the corresponding yield data to derive regression-type yield prediction models for the first and second season crop, respectively. These yield models were then validated with ground truth measurements conducted in 2007 and 2008 at eight sites, of different soil properties, climatic conditions, and various treatments in cultivars planted and N application rates, using surface reflectance retrieved from atmospherically corrected SPOT imageries. These validation tests indicated that root mean square error of predicting grain yields per unit area by the proposed models were less than 0.7 T ha⁻¹ for both cropping seasons. Since village is the basic unit for national rice yield census statistics in Taiwan, the yield models were further used to forecast average regional yields for 14 selected villages and compared with officially reported data. Results indicate that the average yield per unit area at village scale can be forecasted with a root mean square error of 1.1 T ha⁻¹ provided no damaging weather occurred during the final month before actual harvest. The methodology can be applied to other optical sensors with similar spectral bands in the visible/near-infrared and to different geographical regions provided that the relation between yield and spectral index is established.     

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.     

The use of MODIS data to derive acreage estimations for larger fields: A case study in the south-western Rostov region of Russia

Recent developments in remote sensing technology, in particular improved spatial and temporal resolution, open new possibilities for estimating crop acreage over larger areas. Remotely sensed data allow in some cases the estimation of crop acreage statistics independently of sub-national survey statistics, which are sometimes biased and incomplete. This work focuses on the use of MODIS data acquired in 2001/2002 over the Rostov Oblast in Russia, by the Azov Sea. The region is characterised by large agricultural fields of around 75 ha on average. This paper presents a methodology to estimate crop acreage using the MODIS 16-day composite NDVI product. Particular emphasis is placed on a good quality crop mask and a good quality validation dataset. In order to have a second dataset which can be used for cross-checking the MODIS classification a Landsat ETM time series for four different dates in the season of 2002 was acquired and classified. We attempted to distinguish five different crop types and achieved satisfactory and good results for winter crops. Three hundred and sixty fields were identified to be suitable for the training and validation of the MODIS classification using a maximum likelihood classification. A novel method based on a pure pixel field sampling is introduced. This novel method is compared with the traditional hard classification of mixed pixels and was found to be superior.     

Empirical regression models using NDVI, rainfall and temperature data for the early prediction of wheat grain yields in Morocco

In Morocco, no operational system actually exists for the early prediction of the grain yields of wheat (Triticum aestivum L.). This study proposes empirical ordinary least squares regression models to forecast the yields at provincial and national levels. The predictions were based on dekadal (10-daily) NDVI/AVHRR, dekadal rainfall sums and average monthly air temperatures. The Global Land Cover raster map (GLC2000) was used to select only the NDVI pixels that are related to agricultural land. Provincial wheat yields were assessed with errors varying from 80 to 762 kg ha⁻¹, depending on the province. At national level, wheat yield was predicted at the third dekad of April with 73 kg ha⁻¹ error, using NDVI and rainfall. However, earlier forecasts are possible, starting from the second dekad of March with 84 kg ha⁻¹ error, at least 1 month before harvest. At the provincial and national levels, most of the yield variation was accounted for by NDVI. The proposed models can be used in an operational context to early forecast wheat yields in Morocco.     

Monitoring urban growth on the European side of the Istanbul metropolitan area: A case study

Istanbul is the largest city in Turkey with an area of around 5750 km² and a population of around 10.8 M (2000). In 1980, the population was only around 4.7 M and so has more than doubled in only 2 decades. In 2000, around 65% of the population were living on the European side of the city with its large industrial/commercial and trade centres. The population is increasing as a result of both births exceeding deaths and mass immigration. Consequently, planned and unplanned housing are increasing while green areas are decreasing in area. Monitoring urban growth will enable the Municipality of Istanbul to better manage this complex urban area.     

A novel approach to estimate canopy height using ICESat/GLAS data: A case study in the New Forest National Park,UK

The Geoscience Laser Altimeter System (GLAS) aboard Ice, Cloud and land Elevation Satellite (ICESat) is a spaceborne LiDAR sensor. It is the first LiDAR instrument which can digitize the backscattered waveform and offer near global coverage. Among others, scientific objectives of the mission include precise measurement of vegetation canopy heights. Existing approaches of waveform processing for canopy height estimation suggest Gaussian decomposition of the waveform which has the limitation to properly characterize significant peaks and results in discrepant information. Moreover, in most cases, Digital Terrain Models (DTMs) are required for canopy height estimation. This paper presents a new automated method of GLAS waveform processing for extracting vegetation canopy height in the absence of a DTM. Canopy heights retrieved from GLAS waveforms were validated with field measured heights. The newly proposed method was able to explain 79% of variation in canopy heights with an RMSE of 3.18 m, in the study area. The unexplained variation in canopy heights retrieved from GLAS data can be due to errors introduced by footprint eccentricity, decay of energy between emitted and received signals, uncertainty in the field measurements and limited number of sampled footprints.Results achieved with the newly proposed method were encouraging and demonstrated its potential of processing full-waveform LiDAR data for estimating forest canopy height. The study also had implications on future full-waveform spaceborne missions and their utility in vegetation studies.     

Assessing factors impacting the spatial discrepancy of remote sensing based cropland products: A case study in Africa

Many African countries are facing increasing risks of food insecurity due to rising populations. Accurate and timely information on the spatial distribution of cropland is critical for the effective management of crop production and yield forecast. Most recent cropland products (2015 and 2016) derived from multi-source remote sensing data are available for public use. However, discrepancies exist among these cropland products, and the level of discrepancy is particularly high in several Africa regions. The overall goal of this study was to identify and assess the driving factors contributing to the spatial discrepancies among four cropland products derived from remotely sensed data. A novel approach was proposed to evaluate the spatial agreement of these cropland products and assess the impact of environmental factors such as elevation dispersion, field size, land-cover richness and frequency of cloud cover on these spatial differences. Results from this study show that the overall accuracies of the four cropland products are below 65%. In particular, large disagreements are seen on datasets covering Sahel zone and along the West African coasts. This study has identified land-cover richness as the driving factor with the largest contribution to the spatial disagreement among cropland products over Africa, followed by the high frequency of cloud cover, small and fragmented field size, and elevation complexity. To improve the accuracy of future cropland products for African regions, the data producers are encouraged to take a multi-classification approach and incorporate multi-sensors into their cropland mapping processes.     

Remote sensing of Red Mediterranean soils: a case study in the viticultural southern Rhone Valley using SPOT satellite imagery

The aim of this work was to map Red Mediterranean soils, for which no previous mapping approach exists, using optical multispectral satellite remote sensing data. This case study explores the use of SPOT XS images over the viticultural Southern Rhone Valley, France, to map exposed vineyard soils. Field spectral measurements were used to distinguish Red Mediterranean soil surfaces during Spring 1999. A supervised maximum likelihood classification was applied to sparsely vegetated and unvegetated surfaces of two spring images from 1995 and 1997, drawing on the field training set and available soil data. Similar global spatial segmentation was obtained despite different soil surface states on these dates. Classification performances were higher than 84% in both images. Mean classification accuracies of Red Mediterranean soils at seven reference surfaces were 60% in 1995 and 70% in 1997. This suggests that the direct use of optical remote sensing data at medium resolution can be useful for mapping bare Red Mediterranean soils.     

The operational method of filling information gaps in satellite imagery using numerical models

Occurrence of cloud cover over remotely sensed area is a significant limitation in the ocean colour and infra-red remote sensing applications, especially when operational use of such a data is considered. A method for the reconstruction of missing data in remote sensing images has been proposed. It is based on complementing satellite data with the corresponding information from other sources of data, in our tested case it was the ecohydrodynamic model. The method solves the problem the presence of a cloud cover also during an extended period. Unlike in many other similar methods, emphasis has been put on retaining remotely sensed information to a high degree and preserving local phenomena that are usually difficult to capture by other methods than satellite remote sensing. The method has been tested on the Baltic Sea. Sea surface temperature and chlorophyll a concentration estimated from satellite data, ecohydrodynamic models and merged product were compared with in situ data. The algorithm was optimized for the two parameters that are crucial for e.g. creating algae bloom forecasts. The root mean square error (RMSE) of the final product of sea surface temperature was 0.73 °C, whereas of the input satellite images 1.26 °C or 1.33 °C and of model maps 0.89 °C. The error factor of chlorophyll a concentration product was 1.8 mg m⁻³, in comparison to 2.55 mg m⁻³ for satellite input source and 2.28 mg m⁻³ for the model one. The results show that the proposed method well utilizes advantages of both satellite and numerical simulation data sources, at the same time reducing the errors of estimation of merged parameters compared to similar errors for both primary sources. It would be a valuable component of fuzzy logic and rule-based HABs prediction.     

A study on trade-offs between spatial resolution and temporal sampling density for wheat yield estimation using both thermal and calendar time

Within-season forecasting of crop yields is of great economic, geo-strategic and humanitarian interest. Satellite Earth Observation now constitutes a valuable and innovative way to provide spatio-temporal information to assist such yield forecasts. This study explores different configurations of remote sensing time series to estimate of winter wheat yield using either spatially finer but temporally sparser time series (5daily at 100 m spatial resolution) or spatially coarser but denser (300 m and 1 km at daily frequency) time series. Furthermore, we hypothesised that better yield estimations could be made using thermal time, which is closer to the crop physiological development. Time series of NDVI from the PROBA-V instrument, which has delivered images at a spatial resolution of 100 m, 300 m and 1 km since 2013, were extracted for 39 fields for field and 56 fields for regional level analysis across Northern France during the growing season 2014-2015. An asymmetric double sigmoid model was fitted on the NDVI series of the central pixel of the field. The fitted model was subsequently integrated either over thermal time or over calendar time, using different baseline NDVI thresholds to mark the start and end of the cropping season. These integrated values were used as a predictor for yield using a simple linear regression and yield observations at field level. The dependency of this relationship on the spatial pixel purity was analysed for the 100 m, 300 m and 1 km spatial resolution. At field level, depending on the spatial resolution and the NDVI threshold, the adjusted R² ranged from 0.20 to 0.74; jackknifed – leave-one-field-out cross validation – RMSE ranged from 0.6 to 1.07 t/ha and MAE ranged between 0.46 and 0.90 t/ha for thermal time analysis. The best results for yield estimation (adjusted R² = 0.74, RMSE =0.6 t/ha and MAE =0.46 t/ha) were obtained from the integration over thermal time of 100 m pixel resolution using a baseline NDVI threshold of 0.2 and without any selection based on pixel purity. The field scale yield estimation was aggregated to the regional scale using 56 fields. At the regional level, there was a difference of 0.0012 t/ha between thermal and calendar time for average yield estimations. The standard error of mean results showed that the error was larger for a higher spatial resolution with no pixel purity and smaller when purity increased. These results suggest that, for winter wheat, a finer spatial resolution rather than a higher revisit frequency and an increasing pixel purity enable more accurate yield estimations when integrated over thermal time at the field scale and at the regional scale only if higher pixel purity levels are considered. This method can be extended to larger regions, other crops, and other regions in the world, although site and crop-specific adjustments will have to include other threshold temperatures to reflect the boundaries of phenological activity. In general, however, this methodological approach should be applicable to yield estimation at the parcel and regional scales across the world.     

Land surface temperature and emissivity estimation for Urban Heat Island assessment using medium- and low-resolution space-borne sensors: A review

The Urban Heat Island (UHI) phenomenon, a typical characteristic on urban landscapes, has been recognised as a key driver to the transformation of local climate. Reliable retrieval of urban and intra-urban thermal characteristics using satellite thermal data depends on accurate removal of the effects of atmospheric attenuations, angular and land surface emissivity. Several techniques have been proposed to retrieve land surface temperature (LST) from coarse resolution sensors. Medium spatial resolution sensors like the Advanced Space-borne Thermal Emission and Reflection Radiometer and the Landsat series offer a viable option for assessing LST within urban landscapes. This paper reviews the theoretical background of LST estimates from the thermal infrared part of the electromagnetic spectrum, LST retrieval algorithms applicable to each of the commonly used medium-resolution sensors and required variables for each algorithm. The paper also highlights LST validation techniques and concludes by stipulating the requirements for LST temporal and spatial configuration.     

The impact of persistent volcanic degassing on vegetation: A case study at Turrialba volcano,Costa Rica

Although the impacts of large volcanic eruptions on the global environment have been frequently studied, the impacts of lower tropospheric emissions from persistently degassing volcanoes remain poorly understood. Gas emissions from persistent degassing exceed those from sporadic eruptive activity, and can have significant long-term (years to decades) effects on local and regional scales, both on humans and the environment. Here, we exploit a variety of high temporal and high spatial resolution satellite-based time series and complementary ground-based measurements of element deposition and surveys of species richness, to enable a comprehensive spatio-temporal assessment of sulfur dioxide (SO₂) emissions and their associated impacts on vegetation at Turrialba volcano (Costa Rica) from 2000 to 2013. We observe increased emissions of SO₂ coincident with a decline in vegetation health downwind of the vents, in accordance with the prevalent wind direction at Turrialba. We also find that satellite-derived vegetation indices at various spatial resolutions are able to accurately define the vegetation kill zone, the extent of which is independently confirmed by ground-based sampling, and monitor its expansion over time. In addition, ecological impacts in terms of vegetation composition and diversity and physiological damage to vegetation, all spatially correspond to fumigation by Turrialba’s plume. This study shows that analyzing and relating satellite observations to conditions and impacts on the ground can provide an increased understanding of volcanic degassing, its impacts in terms of the long-term vegetation response and the potential of satellite-based monitoring to inform hazard management strategies related to land use.     

A review of progress in identifying and characterizing biocrusts using proximal and remote sensing

Biocrusts are critical components of desert ecosystems, significantly modifying the surfaces they occupy. The mixture of biological components and soil particles that form the crust, in conjunction with moisture, determines the biocrusts’ spectral signatures. Proximal and remote sensing in complementary spectral regions, namely the reflective region, and the thermal region, have been used to study biocrusts in a non-destructive manner, in the laboratory, in the field, and from space. The objectives of this review paper are to present the spectral characteristics of biocrusts across the optical domain, and to discuss significant developments in the application of proximal and remote sensing for biocrust studies in the last few years. The motivation for using proximal and remote sensing in biocrust studies is discussed. Next, the application of reflectance spectroscopy to the study of biocrusts is presented followed by a review of the emergence of high spectral resolution thermal remote sensing, which facilitates the application of thermal spectroscopy for biocrust studies. Four specific topics at the forefront of proximal and remote sensing of biocrusts are discussed: (1) The use of remote sensing in determining the role of biocrusts in global biogeochemical cycles; (2) Monitoring the inceptive establishment of biocrusts; (3) Identifying and characterizing biocrusts using Longwave infrared spectroscopy; and (4) Diurnal emissivity dynamics of biocrusts in a sand dune environment. The paper concludes by identifying innovative technologies such as low altitude and high resolution imagery that are increasingly used in remote sensing science, and are expected to be used in future biocrusts studies.     

基于光能利用效率的区域蒸散量反演模型——以玉米种植区为例

以内蒙古河套地区解放闸灌域为研究区域,以实测生物量与土壤含水量及其关系方程为研究基础,建立了基于光能利用效率(radiation use efficiency,RUE)的区域蒸散量反演模型;以陆面能量平衡(surface energy balance algorithm for land,SEBAL)模型为参考,对反演的同一时期的区域蒸散量进行对比分析.结果表明:RUE与SEBAL模型反演的区域蒸散量在空间分布和纹理特征方面具有相似性且相关性较高,决定系数高于农业技术推广支持系统(decision support system for agrotechnology transfer,DSSAT)与SEBAL的;基于RUE建立的区域蒸散量反演模型能够较好地反映区域蒸散量,在监测区植被(或作物)单一的前提下,是一种有效方法.     

An integrated remote sensing and GIS approach for monitoring areas affected by selective logging: A case study in northern Mato Grosso,Brazilian Amazon

Forest cover disturbances due to processes such as logging and forest fires are a widespread issue especially in the tropics, and have heavily affected forest biomass and functioning in the Brazilian Amazon in the past decades. Satellite remote sensing has played a key role for assessing logging activities in this region; however, there are still remaining challenges regarding the quantification and monitoring of these processes affecting forested lands. In this study, we propose a new method for monitoring areas affected by selective logging in one of the hotspots of Mato Grosso state in the Brazilian Amazon, based on a combination of object-based and pixel-based classification approaches applied on remote sensing data. Logging intensity and changes over time are assessed within grid cells of 300 m × 300 m spatial resolution. Our method encompassed three main steps: (1) mapping forest/non-forest areas through an object-based classification approach applied to a temporal series of Landsat images during the period 2000–2015, (2) mapping yearly logging activities from soil fraction images on the same Landsat data series, and (3) integrating information from previous steps within a regular grid-cell of 300 m × 300 m in order to monitor disturbance intensities over this 15-years period. The overall accuracy of the baseline forest/non-forest mask (year 2000) and of the undisturbed vs disturbed forest (for selected years) were 93% and 84% respectively. Our results indicate that annual forest disturbance rates, mainly due to logging activities, were higher than annual deforestation rates during the whole period of study. The deforested areas correspond to circa 25% of the areas affected by forest disturbances. Deforestation rates were highest from 2001 to 2005 and then decreased considerably after 2006. In contrast, the annual forest disturbance rates show high temporal variability with a slow decrease over the 15-year period, resulting in a significant increase of the ratio between disturbed and deforested areas. Although the majority of the areas, which have been affected by selective logging during the period 2000–2014, were not deforested by 2015, more than 70% of the deforested areas in 2015 had been at least once identified as disturbed forest during that period.     

Wavelet-based detection of bush encroachment in a savanna using multi-temporal aerial photographs and satellite imagery

Although increased woody plant abundance has been reported in tropical savannas worldwide, techniques for detecting the direction and magnitude of change are mostly based on visual interpretation of historical aerial photography or textural analysis of multi-temporal satellite images. These techniques are prone to human error and do not permit integration of remotely sensed data from diverse sources. Here, we integrate aerial photographs with high spatial resolution satellite imagery and use a discrete wavelet transform to objectively detect the dynamics in bush encroachment at two protected Zimbabwean savanna sites. Based on the recently introduced intensity-dominant scale approach, we test the hypotheses that: (1) the encroachment of woody patches into the surrounding grassland matrix causes a shift in the dominant scale. This shift in the dominant scale can be detected using a discrete wavelet transform regardless of whether aerial photography and satellite data are used; and (2) as the woody patch size stabilises, woody cover tends to increase thereby triggering changes in intensity. The results show that at the first site where tree patches were already established (Lake Chivero Game Reserve), between 1972 and 1984 the dominant scale of woody patches initially increased from 8 m before stabilising at 16 m and 32 m between 1984 and 2012 while the intensity fluctuated during the same period. In contrast, at the second site, which was formely grass-dominated site (Kyle Game Reserve), we observed an unclear dominant scale (1972) which later becomes distinct in 1985, 1996 and 2012. Over the same period, the intensity increased. Our results imply that using our approach we can detect and quantify woody/bush patch dynamics in savanna landscapes.     

地面站点叶面积指数观测的空间代表性评价——以CERN站网观测为例

在叶面积指数LAI(Leaf Area Index)产品真实性检验中,地面站点的多时相连续观测LAI数据是重要的验证数据来源。当站点观测范围与产品像元尺度不一致时,站点观测LAI直接用于产品验证可能为验证结果带来误差。因此,在验证之前需要分析站点观测对像元尺度的空间代表性,选择空间代表性好的观测来验证产品,从而减小尺度效应带来的验证误差。以往的研究只是简单的定性说明研究区域,并直接用站点测量数据对产品进行验证,缺少一套系统的站点观测在产品像元尺度内空间代表性评价的方法体系。本文提出了站点LAI观测的空间代表性评价方法,建立了评价指标DVTP(Dominant Vegetation Type Percent)、RSSE(Relative Spatial Sampling Error)和CS(Coefficient of Sill),构建了空间代表性评价分级体系。以中国生态系统研究网络CERN(Chinese Ecosystem Research Network)农田站和森林站LAI观测为例,对站点观测在1 km产品像元尺度内空间代表性进行评价,并分析评价前后站点观测对MODIS LAI产品验证精度的影响。结果显示,本文提出的方法能够有效地对不同站点LAI观测在产品像元尺度内空间代表性进行质量分级,且年际间的站点观测空间代表性较为一致。评价方法能够去掉在特定产品像元尺度下空间代表性不好的观测数据,一定程度上提高验证数据集对产品验证精度的可靠性。     

Evaluating a satellite-based seasonal evapotranspiration product and identifying its relationship with other satellite-derived products and crop yield: A case study for Ethiopia

Satellite-derived evapotranspiration anomalies and normalized difference vegetation index (NDVI) products from Moderate Resolution Imaging Spectroradiometer (MODIS) data are currently used for African agricultural drought monitoring and food security status assessment. In this study, a process to evaluate satellite-derived evapotranspiration (ETa) products with a geospatial statistical exploratory technique that uses NDVI, satellite-derived rainfall estimate (RFE), and crop yield data has been developed. The main goal of this study was to evaluate the ETa using the NDVI and RFE, and identify a relationship between the ETa and Ethiopia’s cereal crop (i.e., teff, sorghum, corn/maize, barley, and wheat) yields during the main rainy season. Since crop production is one of the main factors affecting food security, the evaluation of remote sensing-based seasonal ETa was done to identify the appropriateness of this tool as a proxy for monitoring vegetation condition in drought vulnerable and food insecure areas to support decision makers. The results of this study showed that the comparison between seasonal ETa and RFE produced strong correlation (R² > 0.99) for all 41 crop growing zones in Ethiopia. The results of the spatial regression analyses of seasonal ETa and NDVI using Ordinary Least Squares and Geographically Weighted Regression showed relatively weak yearly spatial relationships (R² < 0.7) for all cropping zones. However, for each individual crop zones, the correlation between NDVI and ETa ranged between 0.3 and 0.84 for about 44% of the cropping zones. Similarly, for each individual crop zones, the correlation (R²) between the seasonal ETa anomaly and de-trended cereal crop yield was between 0.4 and 0.82 for 76% (31 out of 41) of the crop growing zones. The preliminary results indicated that the ETa products have a good predictive potential for these 31 identified zones in Ethiopia. Decision makers may potentially use ETa products for monitoring cereal crop yields and early warning of food insecurity during drought years for these identified zones.     

Remotely sensed estimation of forest canopy density: A comparison of the performance of four methods

In recent years, a number of alternative methods have been proposed to predict forest canopy density from remotely sensed data. To date, however, it remains difficult to decide which method to use, since their relative performance has never been evaluated. In this study the performance of: (1) an artificial neural network, (2) a multiple linear regression, (3) the forest canopy density mapper and (4) a maximum likelihood classification method was compared for prediction of forest canopy density using a Landsat ETM+ image. Comparison of confusion matrices revealed that the regression model performed significantly worse than the three other methods. These results were based on a z-test for comparison of weighted kappa statistics, which is an appropriate statistic for analysis of ranked categories. About 89% of the variance of the observed canopy density was explained by the artificial neural networks, which outperformed the other three methods in this respect. Moreover, the artificial neural networks gave an unbiased prediction, while other methods systematically under or over predicted forest canopy density. The choice of biased method could have a high impact on canopy density inventories.     

Spectral discrimination of hydrothermally altered materials using ASTER short-wave infrared bands: Evaluation in a tropical savannah environment

ASTER short-wave infrared bands were used to investigate the spectral discrimination of hydrothermally altered materials, based on the presence of minerals with diagnostic spectral features in wavelengths around 2200 nm (e.g. kaolinite and K-micas). Due to the presence of widespread albitized-greisenized materials, the Serra do Mendes granitoid, located in area of tropical savannah environment in Central Brazil, was selected for this study. The Spectral Angle Mapper (SAM) technique was used as an attempt to detect the presence of hydroxyl-bearing minerals in the domain of the hydrothermally altered materials. Results indicated that areas of altered materials were discriminated from the surrounding mainly due to the high overall reflectance of the whitish lithosols in these areas. The detection of hydroxyl-bearing minerals was blurred by the presence of a sparse grass cover in the alteration zone, which caused a slight increase in the SAM classification angles. As a consequence, the remote detection of hydroxyl-bearing minerals was restricted to a small number of pixels from barren areas. Results indicate that, for the environmental conditions of the study area, ASTER data are more efficacious for spectral characterization of rock–soil-vegetation associations than for the detection of alteration-derived minerals.