Effect of agrochemicals on earthworms

Dureja, Prem; Patra, D. D.; Johnson, Sapna; Tomar, S. M. S.

doi:10.1080/02772249909358810

“…Earthworms can also be used as bioindicators for soil pollution (Bullinger-Weber et al, 2012;Dureja et al, 1999;Suthar et al, 2008;Wang et al, 2009). In general, bioindicators are used to estimate the quality of the environment.…”

Section: Introductionmentioning

confidence: 99%

Effects of aluminum and moisture levels on aluminum bioaccumulation and protein content in the earthworm Octodrilus complanatus

Bilalis

¹

,

Tzortzi

²

,

Vavoulidou

³

et al. 2013

J. Soil Sci. Plant Nutr.

View full text Add to dashboard Cite

Laboratory experiments were conducted to determine the effects of soil aluminum levels and moisture content on aluminum (Al) bioaccumulation and protein content in the earthworm (Octodrilus complanatus). The experimental design was a completely randomized block with 2 factors (aluminum content [C-0: 0 mg kg -1 , C-1: 1000 mg kg -1 , C-2: 2000 mg kg -1 , C-3: 3000 mg kg -1 ] and moisture level [M1: 100% of soil water capacity, M2: 60% of soil water capacity] and 3 replications. The lowest pH was noted in the C-0 treatment. There were no significant differences in the electrical conductivity, cation exchange capacity or total nitrogen in soil between the aluminum treatments. Moreover, there were no significant differences in soil properties between the moisture treatments. The highest soil Al content was noted in the C-3 treatment. No earthworm mortality was observed in soil contaminated with Al. Moreover, the highest aluminum content in earthworms was observed in the C-3 treatment. The aluminum content in the earthworms was significantly positively correlated with the aluminum content in the soil (r=0.984***, p<0.001). Our results indicated that the growth of earthworms was affected by the Al level. Lastly, Al caused a reduction in earthworm protein content.

show abstract

“…Hence it becomes necessary to selectively remove these plants to ensure a healthy crop yield [1], [2]. However, the traditional practice of treating the entire farmland indiscriminately with agrochemicals for weed control, in addition to being expensive, adversely impacts the soil biodiversity, quality of freshwater available to humans as well as the human health [3]- [6]. An alternative to chemical weeding is to manually pick the weed plants (manual weeding).…”

Section: Introductionmentioning

confidence: 99%

Weed Density and Distribution Estimation for Precision Agriculture Using Semi-Supervised Learning

Shorewala

¹

,

Ashfaque

²

,

Sidharth

³

et al. 2021

View full text Add to dashboard Cite

Uncontrolled growth of weeds can severely affect the crop yield and quality. Unrestricted use of herbicide for weed removal alters biodiversity and cause environmental pollution. Instead, identifying weed-infested regions can aid selective chemical treatment of these regions. Advances in analyzing farm images have resulted in solutions to identify weed plants. However, a majority of these approaches are based on supervised learning methods which requires huge amount of manually annotated images. As a result, these supervised approaches are economically infeasible for the individual farmer because of the wide variety of plant species being cultivated. In this paper, we propose a deep learning-based semi-supervised approach for robust estimation of weed density and distribution across farmlands using only limited color images acquired from autonomous robots. This weed density and distribution can be useful in a site-specific weed management system for selective treatment of infected areas using autonomous robots. In this work, the foreground vegetation pixels containing crops and weeds are first identified using a Convolutional Neural Network (CNN) based unsupervised segmentation. Subsequently, the weed infected regions are identified using a fine-tuned CNN, eliminating the need for designing hand-crafted features. The approach is validated on two datasets of different crop/weed species (1) Crop Weed Field Image Dataset (CWFID), which consists of carrot plant images and the (2) Sugar Beets dataset. The proposed method is able to localize weed-infested regions a maximum recall of 0.99 and estimate weed density with a maximum accuracy of 82.13%. Hence, the proposed approach is shown to generalize to different plant species without the need for extensive labeled data.

show abstract

“…Hence it becomes necessary to selectively remove these plants to ensure a healthy crop yield [1], [2]. However, the traditional practice of treating the entire farmland indiscriminately with agrochemicals for weed control, in addition to being expensive, adversely impacts the soil biodiversity, quality of freshwater available to humans as well as the human health [3]- [6].…”

Section: Introductionmentioning

confidence: 99%

“…However, the use of hand crafted features restricts the usage of these approaches to a particular crop/weed species. The major challenges to a reliable, scalable vision system for the autonomous robots are (1) varying lighting conditions, (2) overlapping and occluded weed and crop plants, (3) varying weed density, and (4) different species of crop and weed plants. In addition, the supervised learning-based approach depends on the availability of annotated data.…”

Section: Introductionmentioning

confidence: 99%

Weed Density and Distribution Estimation for Precision Agriculture using Semi-Supervised Learning

Shorewala,

Ashfaque,

R

et al. 2020

Preprint

0

View full text Add to dashboard Cite

Uncontrolled growth of weeds can severely affect the crop yield and quality. Unrestricted use of herbicide for weed removal alters biodiversity and cause environmental pollution. Instead, identifying weed-infested regions can aid selective chemical treatment of these regions. Advances in analyzing farm images have resulted in solutions to identify weed plants. However, a majority of these approaches are based on supervised learning methods which requires huge amount of manually annotated images. As a result, these supervised approaches are economically infeasible for the individual farmer because of the wide variety of plant species being cultivated. In this paper, we propose a deep learning-based semi-supervised approach for robust estimation of weed density and distribution across farmlands using only limited color images acquired from autonomous robots. This weed density and distribution can be useful in a site-specific weed management system for selective treatment of infected areas using autonomous robots. In this work, the foreground vegetation pixels containing crops and weeds are first identified using a Convolutional Neural Network (CNN) based unsupervised segmentation. Subsequently, the weed infected regions are identified using a fine-tuned CNN, eliminating the need for designing hand-crafted features. The approach is validated on two datasets of different crop/weed species (1) Crop Weed Field Image Dataset (CWFID), which consists of carrot plant images and the (2) Sugar Beets dataset. The proposed method is able to localize weed-infested regions a maximum recall of 0.99 and estimate weed density with a maximum accuracy of 82.13%. Hence, the proposed approach is shown to generalize to different plant species without the need for extensive labeled data.

show abstract

Effect of agrochemicals on earthworms

Cited by 6 publications

References 21 publications

Effects of aluminum and moisture levels on aluminum bioaccumulation and protein content in the earthworm Octodrilus complanatus

Effects of aluminum and moisture levels on aluminum bioaccumulation and protein content in the earthworm Octodrilus complanatus

Weed Density and Distribution Estimation for Precision Agriculture Using Semi-Supervised Learning

Weed Density and Distribution Estimation for Precision Agriculture using Semi-Supervised Learning

Contact Info

Product

Resources

About