Onisimo Mutanga

Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: a review

Wetland vegetation plays a key role in the ecological functions of wetland environments. Remote sensing techniques offer timely, up-to-date, and relatively accurate information for sustainable and effective management of wetland vegetation. This article provides an overview on the status of remote sensing applications in discriminating and mapping wetland vegetation, and estimating some of the biochemical and biophysical parameters of wetland vegetation. Research needs for successful applications of remote sensing in wetland vegetation mapping and the major challenges are also discussed. The review focuses on providing fundamental information relating to the spectral characteristics of wetland vegetation, discriminating wetland vegetation using broad- and narrow-bands, as well as estimating water content, biomass, and leaf area index. It can be concluded that the remote sensing of wetland vegetation has some particular challenges that require careful consideration in order to obtain successful results. These include an in-depth understanding of the factors affecting the interaction between electromagnetic radiation and wetland vegetation in a particular environment, selecting appropriate spatial and spectral resolution as well as suitable processing techniques for extracting spectral information of wetland vegetation.

Narrow band vegetation indices overcome the saturation problem in biomass estimation

Remotely sensed vegetation indices such as NDVI, computed using the red and near infrared bands have been used to estimate pasture biomass. These indices are of limited value since they saturate in dense vegetation. In this study, we evaluated the potential of narrow band vegetation indices for characterizing the biomass of Cenchrus ciliaris grass measured at high canopy density. Three indices were tested: Modified Normalized Difference Vegetation Index (MNDVI), Simple Ratio (SR) and Transformed Vegetation Index (TVI) involving all possible two band combinations between 350 nm and 2500 nm. In addition, we evaluated the potential of the red edge position in estimating biomass at full canopy cover. Results indicated that the standard NDVI involving a strong chlorophyll absorption band in the red region and a near infrared band performed poorly in estimating biomass (R 2=0.26). The MNDVIs involving a combination of narrow bands in the shorter wavelengths of the red edge (700–750 nm) and longer wavelengths of the red edge (750–780 nm), yielded higher correlations with biomass (mean R 2=0.77 for the highest 20 narrow band NDVIs). When the three vegetation indices were compared, SR yielded the highest correlation coefficients with biomass as compared to narrow band NDVI and TVI (average R 2=0.80, 0.77 and 0.77 for the first 20 ranked SR, NDVI and TVI respectively). The red edge position yielded comparable results to the narrow band vegetation indices involving the red edge bands. These results indicate that at high canopy density, pasture biomass may be more accurately estimated by vegetation indices based on wavelengths located in the red edge than the standard NDVI.

High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm

a b s t r a c t The saturation problem associated with the use of NDVI for biomass estimation in high canopy density vegetation is a well known phenomenon. Recent field spectroscopy experiments have shown that narrow band vegetation indices computed from the red edge and the NIR shoulder can improve the estimation of biomass in such situations. However, the wide scale unavailability of high spectral resolution satel- lite sensors with red edge bands has not seen the up-scaling of these techniques to spaceborne remote sensing of high density biomass. This paper explored the possibility of estimate biomass in a densely veg- etated wetland area using normalized difference vegetation index (NDVI) computed from WorldView-2 imagery, which contains a red edge band centred at 725 nm. NDVI was calculated from all possible two band combinations of WorldView-2. Subsequently, we utilized the random forest regression algorithm as variable selection and a regression method for predicting wetland biomass. The performance of random forest regression in predicting biomass was then compared against the widely used stepwise multiple linear regression. Predicting biomass on an independent test data set using the random forest algorithm and 3 NDVIs computed from the red edge and NIR bands yielded a root mean square error of prediction (RMSEP) of 0.441 kg/m 2 (12.9% of observed mean biomass) as compared to the stepwise multiple lin- ear regression that produced an RMSEP of 0.5465 kg/m2 (15.9% of observed mean biomass). The results demonstrate the utility of WorldView-2 imagery and random forest regression in estimating and ulti- mately mapping vegetation biomass at high density - a previously challenging task with broad band satellite sensors.

Discriminating tropical grass (Cenchrus ciliaris) canopies grown under different nitrogen treatments using spectroradiometry

Techniques for estimating and mapping pasture quality are critical for a better understanding of wildlife and livestock grazing patterns. Nitrogen is one of the most important elements that determine quality in plants. We assessed the potential to discriminate differences in nitrogen concentration using high-resolution reflectance by growing Cenchrus ciliaris grass with different fertilization treatments in a greenhouse. Canopy spectral measurements from each treatment were taken under controlled laboratory conditions within a period of 4 weeks using a GER 3700 spectroradiometer. Results show that there were statistically significant differences in spectral reflectance between treatments within certain wavelength regions—an encouraging result for classifying and mapping grasslands with different levels of nutrients using hyperspectral remote sensing. We further investigated the effect of varying nitrogen supply to a specific absorption feature in the visible between 550 and 750 nm (R550– 750) using continuum-removed spectra. Results show that the high nitrogen treatment had deeper and wider absorption pits as compared to the low nitrogen treatment as well as the control (no nitrogen), which is important for the prediction of nitrogen in grass canopies. This is a promising result for the remote sensing of canopy chemistry since emphasis can be shifted from the mid-infrared region (which is highly masked by water absorption) to the visible region. Overall, the results provide the possibility to map variation in pasture quality using hyperspectral remote sensing.

A comparison of regression tree ensembles: Predicting Sirex noctilio induced water stress in Pinus patula forests of KwaZulu-Natal, South Africa

In this study we compared the performance of regression tree ensembles using hyperspectral data. More specifically, we compared the performance of bagging, boosting and random forest to predict Sirex noctilio induced water stress in Pinus patula trees using nine spectral parameters derived from hyperspectral data. Results from the study show that the random forest ensemble achieved the best overall performance (R 2 = 0.73) and that the predictive accuracy of the ensemble was statistically different (p < 0.001) from bagging and boosting. Additionally, by using random forest as a wrapper we simplified the modeling process and identified the minimum number (n = 2) of spectral parameters that offered the best overall predictive accuracy (R 2 = 0.76). The water index and Ratio975 had the best ability to assay the water status of S. noctilio infested trees thus making it possible to remotely predict and quantify the severity of damage caused by the wasp.

Land-use/cover classification in a heterogeneous coastal landscape using RapidEye imagery: evaluating the performance of random forest and support vector machines classifiers

Mapping of patterns and spatial distribution of land-use/cover (LULC) has long been based on remotely sensed data. In the recent past, efforts to improve the reliability of LULC maps have seen a proliferation of image classification techniques. Despite these efforts, derived LULC maps are still often judged to be of insufficient quality for operational applications, due to disagreement between generated maps and reference data. In this study we sought to pursue two objectives: first, to test the new-generation multispectral RapidEye imagery classification output using machine-learning random forest (RF) and support vector machines (SVM) classifiers in a heterogeneous coastal landscape; and second, to determine the importance of different RapidEye bands on classification output. Accuracy of the derived thematic maps was assessed by computing confusion matrices of the classifiers’ cover maps with respective independent validation data sets. An overall classification accuracy of 93.07% with a kappa value of 0.92, and 91.80 with a kappa value of 0.92 was achieved using RF and SVM, respectively. In this study, RF and SVM classifiers performed comparatively similarly as demonstrated by the results of McNemer’s test (Z = 1.15). An evaluation of different RapidEye bands using the two classifiers showed that incorporation of the red-edge band has a significant effect on the overall classification accuracy in vegetation cover types. Consequently, pursuit of high classification accuracy using high-spatial resolution imagery on complex landscapes remains paramount.

Discriminating the papyrus vegetation Cyperus papyrus L. and its co-existent species using random forest and hyperspectral data resampled to HYMAP

Techniques for discriminating swamp wetland species are critical for the rapid assessment and proactive management of wetlands. In this study, we tested whether the random forest (RF) algorithm could discriminate between papyrus swamp and its co-existent species (Phragmites australis, Echinochloa pyramidalis and Thelypteris interrupta) using in situ canopy reflectance spectra. Canopy spectral measurements were taken from the species using analytical spectral devices but later resampled to Hyperspectral Mapper (HYMAP) resolution. The RF algorithm and a simple forward variable selection (FVS) technique were used to identify key wavelengths for discriminating papyrus swamp and its co-existence species. The method yielded 10 wavelengths located in the visible and short-wave infrared portions of the electromagnetic spectrum with a lowest out-of-bag (OOB) estimate error rate of 9.5% and .632+ bootstrap error of 8.95%. The use of RF as a classification algorithm resulted in overall accuracy of 90.50% and a kappa value of 0.87, with individual class accuracies ranging from 93.73% to 100%. Additionally, the results from this study indicate that the RF algorithm produces better classification results than conventional classification trees (CTs) when using all HYMAP wavelengths (n = 126) and when using wavelengths selected by the FVS technique.

Intra-and-Inter Species Biomass Prediction in a Plantation Forest: Testing the Utility of High Spatial Resolution Spaceborne Multispectral RapidEye Sensor and Advanced Machine Learning Algorithms

The quantification of aboveground biomass using remote sensing is critical for better understanding the role of forests in carbon sequestration and for informed sustainable management. Although remote sensing techniques have been proven useful in assessing forest biomass in general, more is required to investigate their capabilities in predicting intra-and-inter species biomass which are mainly characterised by non-linear relationships. In this study, we tested two machine learning algorithms, Stochastic Gradient Boosting (SGB) and Random Forest (RF) regression trees to predict intra-and-inter species biomass using high resolution RapidEye reflectance bands as well as the derived vegetation indices in a commercial plantation. The results showed that the SGB algorithm yielded the best performance for intra-and-inter species biomass prediction; using all the predictor variables as well as based on the most important selected variables. For example using the most important variables the algorithm produced an R2 of 0.80 and RMSE of 16.93 t·ha−1 for E. grandis; R2 of 0.79, RMSE of 17.27 t·ha−1 for P. taeda and R2 of 0.61, RMSE of 43.39 t·ha−1 for the combined species data sets. Comparatively, RF yielded plausible results only for E. dunii (R2 of 0.79; RMSE of 7.18 t·ha−1). We demonstrated that although the two statistical methods were able to predict biomass accurately, RF produced weaker results as compared to SGB when applied to combined species dataset. The result underscores the relevance of stochastic models in predicting biomass drawn from different species and genera using the new generation high resolution RapidEye sensor with strategically positioned bands.

Exploiting machine learning algorithms for tree species classification in a semiarid woodland using RapidEye image

Abstract Classification of different tree species in semiarid areas can be challenging as a result of the change in leaf structure and orientation due to soil moisture constraints. Tree species mapping is, however, a key parameter for forest management in semiarid environments. In this study, we examined the suitability of 5-band RapidEye satellite data for the classification of five tree species in mopane woodland of Botswana using machine leaning algorithms with limited training samples.We performed classification using random forest (RF) and support vector machines (SVM) based on EnMap box. The overall accuracies for classifying the five tree species was 88.75 and 85% for both SVM and RF, respectively. We also demonstrated that the new red-edge band in the RapidEye sensor has the potential for classifying tree species in semiarid environments when integrated with other standard bands. Similarly, we observed that where there are limited training samples, SVM is preferred over RF. Finally, we demonstrated that the two accuracy measures of quantity and allocation disagreement are simpler and more helpful for the vast majority of remote sensing classification process than the kappa coefficient. Overall, high species classification can be achieved using strategically located RapidEye bands integrated with advanced processing algorithms.

Integrating remote sensing and spatial statistics to model herbaceous biomass distribution in a tropical savanna

Modelling herbaceous biomass is critical for an improved understanding of wildlife feeding patterns and distribution as well as for the development of early warning systems for fire management. Most savannas in South Africa are characterized by complex stand structure and abundant vegetation species. This has prohibited accurate estimation of biomass in such environments. We investigated the possibility of improving biomass predictions in tropical savannas using cokriging. Individual bands and ratios computed from Moderate Resolution Imaging Spectroradiometer (MODIS) imagery were correlated with field measurements of biomass covering the Kruger National Park, South Africa. The band that yielded the highest correlation with biomass was then used for further analysis using cokriging. Three variogram models were developed: one for the herbaceous biomass, one for the best MODIS band and a cross variogram between all pairs of variables involved in the estimation. The variogram models were then used in cokriging to predict biomass distribution over the whole study area. Results indicate that a combination of remotely sensed data with field biomass measurements through cokriging improves the estimation accuracy compared to ordinary kriging and stepwise linear regression. Given the high temporal resolution of the freely available MODIS imagery, the result is critical for the improved monitoring and management of wildlife habitats.