Estimate of winter-wheat above-ground biomass based on UAV ultrahigh-ground-resolution image textures and vegetation indices

Assessment of forest above ground biomass (AGB) is critical for managing forest and understanding the role of forest as source of carbon fluxes. Recently, satellite remote sensing products offer the chance to map forest biomass and carbon stock. The present study focuses on comparing the potential use of combination of ALOSPALSAR and Sentinel-1 SAR data, with Sentinel-2 optical data to estimate above ground biomass and carbon stock using Genetic-Random forest machine learning (GA-RF) algorithm. Polarimetric decompositions, texture characteristics and backscatter coefficients of ALOSPALSAR and Sentinel-1, and vegetation indices, tasseled cap, texture parameters and principal component analysis (PCA) of Sentinel-2 based on measured AGB samples were used to estimate biomass. The overall coefficient (R2) of AGB modelling using combination of ALOSPALSAR and Sentinel-1 data, and Sentinel-2 data were respectively 0.70 and 0.62. The result showed that Combining ALOSPALSAR and Sentinel-1 data to predict AGB by using GA-RF model performed better than Sentinel-2 data.

Download Full-text

Application of Convolutional Neural Network on Lei Bamboo Above-Ground-Biomass (AGB) Estimation Using Worldview-2

Remote Sensing ◽

10.3390/rs12060958 ◽

2020 ◽

Vol 12 (6) ◽

pp. 958 ◽

Cited By ~ 2

Author(s):

Luofan Dong ◽

Huaqiang Du ◽

Ning Han ◽

Xuejian Li ◽

Di’en Zhu ◽

...

Keyword(s):

Neural Network ◽

High Resolution ◽

Spatial Data ◽

Vegetation Indices ◽

Spatial Data Analysis ◽

Support Vector ◽

Above Ground Biomass ◽

Ground Biomass ◽

State Of Art ◽

Combined Data

Above-ground biomass (AGB) directly relates to the productivity of forests. Precisely, AGB mapping for regional forests based on very high resolution (VHR) imagery is widely needed for evaluation of productivity. However, the diversity of variables and algorithms and the difficulties inherent in high resolution optical imagery make it complex. In this paper, we explored the potentials of the state-of-art algorithm convolutional neural networks (CNNs), which are widely used for its high-level representation, but rarely applied for AGB estimation. Four experiments were carried out to compare the performance of CNNs and other state-of-art Machine Learning (ML) algorithms: (1) performance of CNN using bands, (2) performance of Random Forest (RF), support vector regression (SVR), artificial neural network (ANN) on bands, and vegetation indices (VIs). (3) Performance of RF, SVR, and ANN on gray-level co-occurrence matrices (GLCM), and exploratory spatial data analysis (ESDA), and (4) performance of RF, SVR, and ANN based on all combined data and ESDA+VIs. CNNs reached satisfactory results (with R2 = 0.943) even with limited input variables (i.e., only bands). In comparison, RF and SVR with elaborately designed data obtained slightly better accuracy than CNN. For examples, RF based on GLCM textures reached an R2 of 0.979 and RF based on all combined data reached a close R2 of 0.974. However, the results of ANN were much worse (with the best R2 of 0.885).

Download Full-text

Growth and yield response of winter wheat to soil warming and rainfall patterns

The Journal of Agricultural Science ◽

10.1017/s0021859610000419 ◽

2010 ◽

Vol 148 (5) ◽

pp. 553-566 ◽

Cited By ~ 38

Author(s):

R. H. PATIL ◽

M. LAEGDSMAND ◽

J. E. OLESEN ◽

J. R. PORTER

Keyword(s):

Climate Change ◽

Soil Moisture ◽

Winter Wheat ◽

Rainfall Amount ◽

Growth And Yield ◽

Above Ground Biomass ◽

Soil Warming ◽

Ground Biomass ◽

Rainfall Frequency ◽

Crop Development

SUMMARYIt is predicted that climate change will increase not only seasonal air and soil temperatures in northern Europe but also the variability of rainfall patterns. This may influence temporal soil moisture regimes and the growth and yield of winter wheat. A lysimeter experiment was carried out in 2008/09 with three factors: rainfall amount, rainfall frequency and soil warming (two levels in each factor), on sandy loam soil in Denmark. The soil warming treatment included non-heated as the control and an increase in soil temperature by 5°C at 100 mm depth as heated. The rainfall treatment included the site mean for 1961–90 as the control and the projected monthly mean change for 2071–2100 under the International Panel on Climate Change (IPCC) A2 scenario for the climate change treatment. Projected monthly mean changes in rainfall compared to the reference period 1961–90 show, on average, 31% increase during winter (November–March) and 24% decrease during summer (July–September) with no changes during spring (April–June). The rainfall frequency treatment included mean monthly rainy days for 1961–90 as the control and a reduced frequency treatment with only half the number of rainy days of the control treatment, without altering the monthly mean rainfall amount. Mobile rain-out shelters, automated irrigation system and insulated heating cables were used to impose the treatments.Soil warming hastened crop development during early stages (until stem elongation) and shortened the total crop growing season by 12 days without reducing the period taken for later development stages. Soil warming increased green leaf area index (GLAI) and above-ground biomass during early growth, which was accompanied by an increased amount of nitrogen (N) in plants. However, the plant N concentration and its dilution pattern during later developmental stages followed the same pattern in both heated and control plots. Increased soil moisture deficit was observed only during the period when crop growth was significantly enhanced by soil warming. However, soil warming reduced N concentration in above-ground biomass during the entire growing period, except at harvest, by advancing crop development. Soil warming had no effect on the number of tillers, but reduced ear number and increased 1000 grain weight. This did not affect grain yield and total above-ground biomass compared with control. This suggests that genotypes with a longer vegetative period would probably be better adapted to future warmer conditions. The rainfall pattern treatments imposed in the present study did not influence either soil moisture regimes or performance of winter wheat, though the crop receiving future rainfall amount tended to retain more green leaf area. There was no significant interaction between the soil warming and rainfall treatments on crop growth.

Download Full-text

Estimation of Winter Wheat Above-Ground Biomass Using Unmanned Aerial Vehicle-Based Snapshot Hyperspectral Sensor and Crop Height Improved Models

Remote Sensing ◽

10.3390/rs9070708 ◽

2017 ◽

Vol 9 (7) ◽

pp. 708 ◽

Cited By ~ 97

Author(s):

Jibo Yue ◽

Guijun Yang ◽

Changchun Li ◽

Zhenhai Li ◽

Yanjie Wang ◽

...

Keyword(s):

Winter Wheat ◽

Unmanned Aerial Vehicle ◽

Above Ground Biomass ◽

Crop Height ◽

Ground Biomass ◽

Aerial Vehicle ◽

Hyperspectral Sensor

Download Full-text

Clover green manure productivity and weed suppression in an organic grain rotation

Renewable Agriculture and Food Systems ◽

10.1017/s1742170516000430 ◽

2016 ◽

Vol 32 (5) ◽

pp. 474-483 ◽

Cited By ~ 5

Author(s):

Katja Koehler-Cole ◽

James R. Brandle ◽

Charles A. Francis ◽

Charles A. Shapiro ◽

Erin E. Blankenship ◽

...

Keyword(s):

Winter Wheat ◽

White Clover ◽

Green Manure ◽

Red Clover ◽

Late Summer ◽

Weed Suppression ◽

Grain Protein ◽

Above Ground Biomass ◽

Ground Biomass ◽

Sampling Times

AbstractGreen manure crops must produce high biomass to supply biological N, increase organic matter and control weeds. The objectives of our study were to assess above-ground biomass productivity and weed suppression of clover (Trifolium spp.) green manures in an organic soybean [Glycine max (L.) Merr.]-winter wheat (Triticum aestivum L.)-corn (Zea mays L.) rotation in eastern Nebraska in three cycles (2011–12, 2012–13, 2013–14). Treatments were green manure species [red clover (T. pratense L.) and white clover (T. repens L.)] undersown into winter wheat in March and green manure mowing regime (one late summer mowing or no mowing). We measured wheat productivity and grain protein at wheat harvest, and clover and weed above-ground biomass as dry matter (DM) at wheat harvest, 35 days after wheat harvest, in October and in April before clover termination. Winter wheat grain yields and grain protein were not affected by undersown clovers. DM was higher for red than for white clover at most sampling times. Red clover produced between 0.4 and 5.5 Mg ha−1 in the fall and 0.4–5.2 Mg ha−1 in the spring. White clover produced between 0.1 and 2.5 Mg ha−1 in the fall and 0.2–3.1 Mg ha−1 in the spring. Weed DM was lower under red clover than under white clover at most sampling times. In the spring, weed DM ranged from 0.0 to 0.6 Mg ha−1 under red clover and from 0.0 to 3.1 Mg ha−1 under white clover. Mowing did not consistently affect clover or weed DM. For organic growers in eastern Nebraska, red clover undersown into winter wheat can be a productive green manure with good weed suppression potential.

Download Full-text

Estimating Above-Ground Biomass of Maize Using Features Derived from UAV-Based RGB Imagery

Remote Sensing ◽

10.3390/rs11111261 ◽

2019 ◽

Vol 11 (11) ◽

pp. 1261 ◽

Cited By ~ 19

Author(s):

Yaxiao Niu ◽

Liyuan Zhang ◽

Huihui Zhang ◽

Wenting Han ◽

Xingshuo Peng

Keyword(s):

Remote Sensing ◽

Linear Regression ◽

Plant Height ◽

Linear Regression Model ◽

Vegetation Indices ◽

Point Clouds ◽

Above Ground Biomass ◽

Sensing System ◽

Ground Biomass ◽

Application Potential

The rapid, accurate, and economical estimation of crop above-ground biomass at the farm scale is crucial for precision agricultural management. The unmanned aerial vehicle (UAV) remote-sensing system has a great application potential with the ability to obtain remote-sensing imagery with high temporal-spatial resolution. To verify the application potential of consumer-grade UAV RGB imagery in estimating maize above-ground biomass, vegetation indices and plant height derived from UAV RGB imagery were adopted. To obtain a more accurate observation, plant height was directly derived from UAV RGB point clouds. To search the optimal estimation method, the estimation performances of the models based on vegetation indices alone, based on plant height alone, and based on both vegetation indices and plant height were compared. The results showed that plant height directly derived from UAV RGB point clouds had a high correlation with ground-truth data with an R2 value of 0.90 and an RMSE value of 0.12 m. The above-ground biomass exponential regression models based on plant height alone had higher correlations for both fresh and dry above-ground biomass with R2 values of 0.77 and 0.76, respectively, compared to the linear regression model (both R2 values were 0.59). The vegetation indices derived from UAV RGB imagery had great potential to estimate maize above-ground biomass with R2 values ranging from 0.63 to 0.73. When estimating the above-ground biomass of maize by using multivariable linear regression based on vegetation indices, a higher correlation was obtained with an R2 value of 0.82. There was no significant improvement of the estimation performance when plant height derived from UAV RGB imagery was added into the multivariable linear regression model based on vegetation indices. When estimating crop above-ground biomass based on UAV RGB remote-sensing system alone, looking for optimized vegetation indices and establishing estimation models with high performance based on advanced algorithms (e.g., machine learning technology) may be a better way.

Download Full-text