Submitted Successfully!
To reward your contribution, here is a gift for you: A free trial for our video production service.
Thank you for your contribution! You can also upload a video entry or images related to this topic.
Version Summary Created by Modification Content Size Created at Operation
1 -- 3520 2022-08-23 09:20:54 |
2 Reference format revised. -1 word(s) 3519 2022-08-23 10:25:01 |

Video Upload Options

Do you have a full video?


Are you sure to Delete?
If you have any further questions, please contact Encyclopedia Editorial Office.
Behera, S.K.;  Adamchuk, V.I.;  Shukla, A.K.;  Pandey, P.S.;  Kumar, P.;  Shukla, V.;  Thiyagarajan, C.;  Rai, H.K.;  Hadole, S.;  Sachan, A.K.; et al. Scope for Using Proximal Soil Sensing by Indian. Encyclopedia. Available online: (accessed on 20 June 2024).
Behera SK,  Adamchuk VI,  Shukla AK,  Pandey PS,  Kumar P,  Shukla V, et al. Scope for Using Proximal Soil Sensing by Indian. Encyclopedia. Available at: Accessed June 20, 2024.
Behera, Sanjib Kumar, Viacheslav I. Adamchuk, Arvind Kumar Shukla, Punyavrat Suvimalendu Pandey, Pardeep Kumar, Vimal Shukla, Chitdeshwari Thiyagarajan, Hitendra Kumar Rai, Sandeep Hadole, Anil Kumar Sachan, et al. "Scope for Using Proximal Soil Sensing by Indian" Encyclopedia, (accessed June 20, 2024).
Behera, S.K.,  Adamchuk, V.I.,  Shukla, A.K.,  Pandey, P.S.,  Kumar, P.,  Shukla, V.,  Thiyagarajan, C.,  Rai, H.K.,  Hadole, S.,  Sachan, A.K.,  Singh, P.,  Trivedi, V.,  Mishra, A.,  Butail, N.P.,  Kumar, P.,  Prajapati, R.,  Tiwari, K.,  Suri, D., & Sharma, M. (2022, August 23). Scope for Using Proximal Soil Sensing by Indian. In Encyclopedia.
Behera, Sanjib Kumar, et al. "Scope for Using Proximal Soil Sensing by Indian." Encyclopedia. Web. 23 August, 2022.
Scope for Using Proximal Soil Sensing by Indian

Knowledge about spatial distribution patterns of soil attributes is very much needed for site-specific soil nutrient management (SSSNM) under precision agriculture. High spatial heterogeneity exists in the agricultural soils of India due to various reasons. The present practice of assessing the spatial variability of the vast cultivated landscape of India by using traditional soil sampling and analysis is costly and time consuming. Hence, proximal soil sensing (PSS) is an attractive option to assess the plot-scale spatial variability pattern (SVP) of soil attributes for SSSNM. A PSS system, either in a fixed position or mounted on a vehicle (on-the-go), can be used to obtain measurements by having direct contact with soil. PSS measurements provide low-cost and high-density data pertaining to the SVPs of soil attributes. These data can be used to generate digital elevation and soil attribute variability maps at the field scale in a crop production environment. Based on the generated variability maps, locally available and economically feasible agricultural inputs can be applied using variable rate application strategies for sustainable cropping and enhanced farm profit. 

soil sensors precision farming digital soil mapping farmers

1. Introduction

Within the Indian agricultural context, cultivated areas of India consist of both rain-fed and irrigated agro-ecosystems. The average crop productivity of the country has remained low due to several factors including heterogeneous soil characteristics and improper water management. Moreover, India has major soil groups such as red, black, lateritic, alluvial, desert, forest, and hill soils with spatially variable soil physical, chemical, and biological properties. During the 1960s, plant growth of high yielding crop varieties was badly affected due to a deficiency of nitrogen (N). This was followed by a deficiency of both N and phosphorus (P) and, subsequently, zinc (Zn) deficiency became an important factor governing the success or failure of crops. Crops showed a positive response to potassium (K) application despite the medium to high K status of several Indian soils [1]. When crops were fertilized with N/NP, plants suffered from secondary and micronutrient deficiencies, as most of the high analysis fertilizers were devoid of secondary nutrients and micronutrients [2][3][4]. Adoption of intensive cropping practices with inadequate and imbalanced nutrient use, and use of lower amounts of organic manure have led to reductions in crop yields and total factor productivity (ratio of output to weighted average of inputs,) and the emergence of multi-nutrient deficiencies. The productivity was 17.9 kg of cereal grain/kg NPK applied during 1960–1970 and it was reduced to 6.3 kg of grain/kg NPK added during 1990–2000 [5]. This trend was also seen in the case of pulses and oilseeds. In Punjab, wheat yield showed a decline from 4850 kg/ha in 1996 to 4260 kg/ha in 2000. There is a wide gap between nutrients supplied and the uptake by crops. Replenishment of nutrients is not adequately followed in different soil/crop management systems; thus, subclinical or hidden deficiencies of several nutrients have been widely observed, resulting in a decline in the total factor productivity of applied nutrients. Some farmers who apply more than the recommended dose of NPK, still obtain reduced crop productivity due to hidden multiple micronutrient deficiencies, which is a matter of concern. Further, imbalanced or excess addition of fertilizer nutrients results in lowering of nutrient use efficiency and degradation of the soil and the environment [6][7].
Ensuring a proper supply of food and maintaining the sustainability of agricultural production systems are two important challenges for the world [8]. The developing countries such as India are experiencing added pressure due to scarcity of resources, land degradation, and an ever-growing population [9][10]. There is an urgent need for the introduction of new technologies and their adoption in Indian agriculture to meet the food grain production demand of 480 million tons by 2050, with proper management of biotic and abiotic stresses experienced by the crops. In the last several decades, there has been various changes in world agriculture. The developed countries have modernized their agricultural systems with advanced technologies for obtaining higher productivity. However, agriculture in India faces hurdles such as non- or less-adoption of advanced technologies and improper availability and use of inputs for agriculture.
Recent agricultural production needs to be efficient to fulfill the ever-rising demand of quality agricultural produce in a sustainable manner that avoids soil and environment degradation [11][12]. The desired quantities of nutrients and water, which are the key inputs for agricultural production, are needed for best soil/crop management. The requirements of these inputs vary across the landscape due to variations in topography and soil types which ultimately influence crop environments. This requires proper identification and understanding of variations and applications of inputs as per local need. The efficiencies of production systems could be enhanced by accurate recognition and consideration of edaphic variation. On the one hand, variations in the physical, chemical, and biological soil properties are traditionally detected by soil sampling followed by laboratory analysis. This involves a huge cost to collect an adequate number of soil samples for accurate characterization to assess landscape variability. Low soil sampling density due to economic consideration is an important limitation. Moreover, a high-resolution soil-type map is one important tool that is not frequently available in developing countries such as India.
On the other hand, soil sensors provide cost- and time-effective quantitative data as compared with the conventional method of laboratory analysis [13]. These sensors, used in proximal soil sensing (PSS), are handy, wireless, intelligent, and having higher levels of accuracy and energy efficiency. A lot of research is being carried out in different parts of the world to develop proximal soil sensors and their applications. In the process of proximal soil sensing uses a sensor, either in contact or in close range (<2 m) of soil, for in situ estimation of surface or subsurface soil properties.
India is one of the biggest producers and consumers of fertilizers among the different countries of the world [14]. The higher fertilizer consumption in India may be due to large areas under cultivation coupled with the application of uniform doses of fertilizer irrespective of spatial variability of the soil in the same field. Therefore, it is of paramount importance to have a proper understanding of the spatial variability of soil nutrients and other associated properties in order to undertake site-specific soil nutrient management (SSSNM) with optimal fertilizer application. SSSNM results in higher economical production and a reduction in the negative environmental impact. Traditional soil management practices involve the use of soil surveys and sampling followed by laboratory analysis and the adoption of suitable management practices based on the soil test values of the collected samples. These practices will continue to help but they are expensive, time consuming, tedious, and some are qualitative in nature. There is a demand for good quality and inexpensive information through proximal soil sensing for site-specific soil management. This also requires laboratory analysis of some soil samples to calibrate proximal sensing data.

2. Soil Heterogeneity

Soil is a heterogenous mass and the soil properties vary widely from place to place. Factors such as parent material, climate, topography, flora and fauna, and time period influence soil formation and also contribute towards soil variability. Jenny [15] depicted soil as function of soil forming factors: soil = f (cl, o, r, p, t), where, cl, o, r, p, and t represent climate, organism (both plants and animals), relief, parent material, and time, respectively. Similar soil types exist under prevailing similar sets of soil forming factors. Each soil forming factor plays a key role in certain environmental condition. On the one hand, soil in a region is mainly influenced by rainfall, climate, and vegetation distribution. On the other hand, soil in a smaller area is governed by the local distribution of vegetation, microclimate, parent material, and time. Soil surveyors consider that relief or topography and vegetation are indicators during a soil survey program for predicting soil boundaries and properties within a soil boundary. Recently, McBratney et al. [16] outlined the SCORPAN model that can quantitatively express the relations of soil and related environmental factors in a spatial context, which are helpful for digital soil mapping. Soil as soil class or soil attribute at a given time and space encompasses quantitative and empirical functions of sseven covariates such as soil, climate, organism, relief, parent material, age, and spatial location represented by S, C, O, R, P, A, and N, respectively.
Soil class or soil attribute = f (soil, climate, organism, relief, parent material, age, and spatial location).
Variable crop yield in a field is related to soil variability [16]. Therefore, it is important to understand crop growing environments for better management of agricultural fields. As discussed above, interactions of the different soil forming factors result in variability of soil in different scales and in soil profile.
The scale of spatial variability is different for various soil properties. It varies from very short distances, i.e., <1 m (for example, soil nitrate) to several meters and kilometers (for example, soil carbon). 
Soil properties vary with space and time. Some soil properties are very dynamic in nature and keep changing rapidly with time. Whereas, some soil properties are relatively static. Examples of dynamic soil properties are soil temperature, soil moisture, soil solution, nutrient concentrations, soluble salt concentration, etc. Whereas, texture, soil colour, soil depth, and cation exchange capacity are examples of relatively static properties. 

3. Proximal Soil Sensing

Farm managers need to understand and interpret soil physical, chemical, and biological parameters to properly understand the prevailing soil variability. Traditionally, this is carried out by collecting soil samples and subsequently testing in a laboratory. This needs an accurate sampling strategy and appropriate methodologies and equipments. To understand the temporal and spatial variability of soil parameters, model-based soil sampling is useful. Geostatistical techniques are useful for analyzing soil variability, since it is possible to predict the values of soil parameters at unsampled locations using the values of soil parameters at sampled locations [17]. Dense soil sampling is not economically feasible under conventional sampling schemes, but it is needed for accurate capturing of soil variability. Therefore, both proximal and remote sensing techniques have been used to obtain dense spatial resolution which is economically affordable [18]. Proximal soil sensing is carried out by using a sensor close to the soil surface or in close contact with the soil. Whereas, the remote sensing technique involves obtaining data from sensors kept at >2 m away from a targeted object. Normally, the sensors are placed on an aerial platform or a satellite.
Proximal soil sensors are categorized by how they measure and operate, the source of their energy, and the inference used in the measurement of the target soil property. For instance, a proximal soil sensor is said to be invasive if during measurement there is sensor-to-soil contact, otherwise it is non-invasive. If measurements are invasive, then the sensors may be further described as in situ (i.e., the measurements are made within the soil) or ex situ (i.e., the measurements are made on excavated soil, e.g., measurements on soil cores). Proximal soil sensors may be described as being mobile, in which case they measure soil properties while moving or ”on-the-go”, or they may be stationary, whereby measurements are made in a fixed position and possibly at different depths. A proximal soil sensor that produces its own energy from an artificial source for its measurements is said to be active. It is passive if it uses naturally occurring radiation from the sun or earth. If the measurement of the target soil property is based on a physical process, then the proximal soil sensor is said to be direct, but when the measurement is of a proxy and inference is with a pedo-transfer function, then the proximal soil sensor is indirect. 
High-density soil parameter maps can be obtained using proximal soil sensors while moving in the field, which is called on-the-go PSS. There are different types of on-the-go PSS systems. Many of the on-the-go PSS systems use either electrochemical, electrical and electromagnetic, mechanistic and optical, and radiometric sensors [19][20]. Electrochemical sensor contains ion-selective membranes which provide voltage output in response to the activity of some selected ions such as K, nitrate, and hydrogen (H). To measure the activity of targeted ions in soil by assessing the potential differences between reference and sensing part, glass or polymer membrane-based ion-selective electrodes or ion-selective field effect transistors are used. The electrical conductivity or resistivity or capacitance as affected by soil composition is measured by electrical and electromagnetic sensors [21]. Electrical conductivity at multiple soil depths can be sensed using more than two electrodes as the distance between two electrodes determines the effective depth of measurement. The mechanistic sensors are of three types, i.e., mechanical sensors (measure forces resulting from engagement of a tool with soil), acoustic sensors (measure sound due to interactions between a tool and soil), and pneumatic sensors (measure the resistance to air injected into the soil). Soil parameters such as compaction and texture are sensed by considering the movements of air and sound in soil, respectively, by using pneumatic and acoustic sensors. A linear mixed-effect model showed an increase in the acoustic velocity with a decrease in gravimetric moisture content. The acoustic sensing device showed its potential for soil water content monitoring, leading to efficient irrigation planning. Soil mechanical strength can be sensed by mechanical sensors which work on the principle of vertical cone penetrometer. Hemmat et al. [22] developed and field-tested an integrated sensor (instrumented disk coulter and penetrometer) for on-the-go measurement of soil mechanical resistance. With offset positioning of the sensors on the frame, the developed integrated sensor could map the mechanical resistance of soil profile to a depth of 30 cm. The optical and radiometric sensors measured the level of energy reflected or absorbed by the soil particles influenced by different soil parameters. 
Another important aspect of PSS is that crops act as effective sensors to indicate the quality of the prevailing local environmental conditions. Proximal sensing of reflectance from crop canopy can be used to understand the spatial distribution of crop performance in an area which ultimately could be explained by soil heterogeneity. The present research on precision agriculture envisages integration of different crops and soil sensing technologies for effective understanding of the spatial distribution patterns of soil parameters that significantly influence crop yields [23]. Subsequently, required agricultural inputs could be provided by following variable rate application technology as per local needs for better farm profitability and for a sustainable environment.

4. Sensor Fusion

Sensors are transducers that alter signal output under the influence of external phenomena, and also, more or less, under direct impact. However, in most cases, considering the soil structure’s complexity, it is significantly impacted by side effects from different soil properties. All the soil properties cannot be measured using a single sensor. Therefore, it is very much important to select a suitable set of sensors for measurement of certain soil properties [24]. A set of selected sensors could be used in a multi-sensor platform for better performance and coverage of soil parameters. The use of a mobile multi-sensor platform for measuring apparent electrical conductivity and pH together has been reported for the development of lime requirement maps [25][26]. In this system, pH sensors measured soil pH, whereas, apparent electrical conductivity sensors helped in differentiating the lime needs based on electrical conductivity values, which were influenced by soil texture, even at the same levels of pH. This system could be utilized for ameliorating acid soils in India which should enhance crop production, since India has 49 million hectares of land with acid soils [27].

5. Spatially-Differentiated Crop Management

Soil heterogeneity is the combined effect of both natural and anthropogenic factors. The examples of prevailing spatial variabilities of soil parameters at different scales in agricultural soils of India were described earlier. This warrants the need for adoption of different crop management practices based on soil variability of the country. There are two types of variabilities of soil properties, i.e., dynamic (for example soil solution nutrient concentration) and static (soil texture). Therefore, it is very important to make judicious decisions for addressing the variabilities depending upon available resources and economic feasibility. Before undertaking the activities of addressing soil variabilities for spatially differentiated crop management, a farm manger needs to assess the type and degree of variability, area affected by the variability, economic feasibility, and the profits obtained from the adoption of SSSNM options. If the income from SSSNM is significantly higher than the cost incurred, then the farm manger should act to address the variability.

Techniques such as machine learning and artificial intelligence play important roles in interpretation of PSS data to derive thematic soil maps and, ultimately, prescription maps for agricultural inputs and other field management practices [28][29][30]. Machine learning is a subset of artificial intelligence. Artificial intelligence includes machine learning and expert systems. Linear machine learning techniques such as partial least square (PLS) regression model, and nonlinear techniques such as random forest, artificial neural networks, least square support vector machines, support vector machine regression, and the cubist regression model have been used to interpret PSS data [31][32][33]. The extreme machine learning technique is also useful for this purpose [34].

Decisions related to crop management are of three types: strategic, tactical, and operational. The impacts of strategic, tactical, and operational decisions normally last for 10 years, 5 years, and 1 year, respectively [35]. The strategic decisions influence current, as well as future, land management decisions.

Farm mangers need to perform qualitative assessments of the farm operations they intend to conduct for changes in management. The targeted problem must be identified and assessed before undertaking any decision for management. There are several variabilities, namely organic matter, soil acidity, salinity, weather, soil texture, topography, water infiltration, drainage, soil erosion, crop disease, insects, nutrient deficiency, crop cultivar, and weed infestation in crop growing environments that cause variability in yield; remedies for the variabilities are required.

6. The Scope for Proximal Soil Sensing in India

There is ample scope for adoption of PSS in India in view of diverse soil types, climatic conditions, cropping patterns, crop management practices, and ultimately, the ever-increasing demand for higher agricultural production. Issues such as soil erosion, salinization/alkalization, soil acidity, low SOC levels, poor soil fertility, and soil pollution/contamination by toxic substances pose a threat to efficient management of the country’s soil resource for obtaining higher crop productivity [36]. In addition, poor crop productivity, low farm mechanization, and skewed use of farm inputs such as fertilizers, herbicides, and water are very common in Indian agriculture. In crop production, India occupies second, second, first, and second positions in the production of wheat, rice, pulses, and cotton, respectively, in the world scenario. However, the productivity of these crops varies from 38 (wheat) to 138 (pulses) in the world ranking [37][38]. The overall fertilizer consumption rate of India is less as compared with countries such as Egypt, China, Vietnam, and Netherlands. It has been reported that soil test-based application of adequate and balanced proportions of fertilizers (N, P, K, S, and micronutrients) resulted in enhanced crop productivity in several Indian states [39][40]. However, traditional soil sampling and subsequent analysis require huge cost involvement. Therefore, farm mangers apply imbalanced and inadequate fertilizer without soil testing. Again, several Indian states have been using alarmingly high doses of pesticides and fertilizers. For example, Punjab state, occupying 1.5% of the geographical area, uses 7% of the NPK fertilizer and 60% of the herbicides consumed in the country [41][42]. Excess use of agri-inputs and over-exploitation of land resources in these areas pose unique problems, which are serious concerns for the policymakers and planners in India [37]. Therefore, adoption of proximal soil sensing technology in these states could do a lot to improve input use efficiency, crop productivity, and to reduce the negative impact on environment.
There are three significant stages for introducing PSS in Indian agriculture, i.e., present, intermediate, and future stage. Implementation of the PSS technique in India would be a big exercise. However, it would be possible, as Yan et al. [43] detected the variability of soil moisture and soil salinity in coastal areas of China by integrating remote and proximal soil sensing information. The three stages are as follows:
  • The present stage involves establishing uniform soil and crop management practices, specialized institutions, and dedicated manpower, and creating awareness about the PSS concept by using different media.
  • This is followed by the intermediate stage which involves zone-wise PSS and delineation of soil/crop management zones across the country.
  • The future stage would involve fine grid sampling and calibration for the whole of India, and the adoption of SSSNM options.

7. Conclusions

The techniques of proximal soil sensing could be used in India for evaluating static and dynamic variability of soil heterogeneity caused by natural and/or management-induced factors. Proper management of these variabilities can be carried out using the principles of production economics. The farm mangers and crop growers of India need to have an adequate understanding about the different sources of soil heterogeneity. They must be able to make qualitative and quantitative assessments of soil spatial variability. Differentiated area management options may be adopted locally, if addressing soil heterogeneity is found profitable for economical and environmentally sustainable cultivation of crops. The available proximal soil sensing technologies in developed countries will be of great help for improving the understanding of soil heterogeneity and for adopting SSSNM in order to optimize crop production in developing countries including India.


  1. Singh, M.V.; Wanjari, R.H.; Adhikari, T. Nutrient Dynamics, Crop Productivity and Sustainability under Long Term Fertilizer Experiments in India. AICRP LTFE, IISS, Bhopal 2004, 1–120. Available online: (accessed on 12 December 2021).
  2. Kanwar, J.S.; Randhawa, N.S. Micronutrient research in soils and plants in India. A review. ICAR Technol. Bull. 1974, 50, 1–60.
  3. Singh, M.V. Micronutrient management in rice-wheat cropping system. In Proceedings of the Rice-Wheat Consortium Meeting, PDCSR, Modipuram, India, 5–6 May 1990; Volume 1, pp. 133–144.
  4. Behera, S.K.; Shukla, A.K.; Patra, A.K. Best micronutrient management practices for ameliorating micronutrient deficiency and enhance crop productivity. Indian Farming 2019, 69, 11–16.
  5. Singh, M.V.; Behera, S.K. Strategies and issues in developing customized fertilizers in India. Indian J. Fertil. 2013, 9, 52–59.
  6. Aulakh, M.S.; Adhya, T.K. Impact of agricultural activities on emission of greenhouse gases–Indian perspective. In International Conference on Soil, Water and Environmental Quality–Issues and Strategies; Indian Society of Soil Science: New Delhi, India, 2005; pp. 319–335.
  7. Aulakh, M.S.; Khurana, M.P.S.; Singh, D. Water pollution related to agricultural, industrial and urban activities, and its effects on food chain: Case studies from Punjab. J. New Seeds 2009, 10, 112–137.
  8. Diaz-Ambrona, C.G.H.; Maletta, E. Achieving global food security through sustainable development of agriculture and food systems with regard to nutrients, soil, land, and waste management. Curr. Sustain. Renew. Energy Rep. 2014, 1, 57–65.
  9. Alexandratos, N.; Bruinsma, J. World Agriculture Towards 2030/2050: The 2012 Revision; ESA Working paper No. 12-03; FAO: Rome, Italy, 2012.
  10. Pawlak, K.; Kołodziejczak, M. The Role of Agriculture in Ensuring Food Security in Developing Countries: Considerations in the Context of the Problem of Sustainable Food Production. Sustainability 2020, 12, 5488.
  11. Gomiero, T. Soil degradation, land scarcity and food security: Reviewing a complex challenge. Sustainability 2016, 8, 281.
  12. Miner, G.L.; Delgado, J.A.; Ippolito, J.A.; Stewart, C.E.; Manter, D.K.; Grosso, S.J.D.; Floyd, B.A.; D’Amato, R.E. Assessing manure and inorganic nitrogen fertilization impacts on soil health, crop productivity, and crop quality in a continuous maize agroecosystem. J. Soil Water Conserv. 2020, 75, 481–498.
  13. Viscarra Rossel, R.A.; Adamchuk, V.I.; Sudduth, K.; McKenzie, N.J.; Lobsey, C. Proximal soil sensing: An effective approach for soil measurements in space and time. Adv. Agron. 2011, 113, 243–291.
  14. Shukla, A.K.; Behera, S.K.; Chaudhari, S.K.; Singh, G. Fertilizer use in Indian agriculture and its impact on human health and environment. Indian J. Fertil. 2022, 18, 218–237.
  15. Jenny, H. Factors of Soil Formation: A System of Quantitative Pedology; McGraw-Hill: New York, NY, USA, 1941.
  16. McBratney, A.B.; Mendonca Santos, M.L.; Minasny, B. On digital soil mapping. Geoderma 2003, 117, 3–52.
  17. De Gruijter, J.; Brus, D.J.; Bierkens, M.F.P.; Knotters, M. Sampling for Natural Resource Monitoring; Springer: New York, NY, USA, 2006.
  18. McBratney, A.B.; Whelan, B.; Ancev, T.; Bouma, J. Future directions of precision agriculture. Precis. Agric. 2005, 6, 7–23.
  19. Adamchuk, V.; Viscarra Rossel, R. Development of On-the-Go Proximal Soil Sensor Systems. In Proximal Soil Sensing: Progress in Soil Science; Viscarra Rossel, R., McBratney, A., Minasny, B., Eds.; Springer: Dordrecht, The Netherlands, 2010.
  20. Viscarra Rossel, R.A.; McBratney, A.B.; Minasny, B. Proximal Soil Sensing; Springer: Dordrecht, The Netherlands, 2010.
  21. Corwin, D.L.; Lesch, S.M. Apparent soil electrical conductivity measurements in agriculture. Comput. Electron. Agric. 2005, 46, 11–43.
  22. Hemmat, A.; Binandeh, A.R.; Ghaisari, J.; Khorsandi, A. Development and field testing of an integrated sensor for on-the-go measurement of soil mechanical resistance. Sens. Actuators A Phys. 2013, 198, 61–68.
  23. Yost, M.A.; Kitchen, N.R.; Sudduth, K.A.; Massey, R.E.; Sadler, E.J.; Drummond, S.T.; Volkmann, M.R. A long-term precision agriculture system sustains grain profitability. Precis. Agric. 2019, 20, 1177–1198.
  24. Mahmood, H.S.; Hoogmoed, W.B.; van Henten, E.J. Sensor data fusion to predict multiple soil properties. Precis. Agric. 2012, 13, 628–645.
  25. Lund, E.D.; Adamchuk, V.I.; Collings, K.L.; Drummond, P.E.; Christy, C.D. Development of soil pH and lime requirement maps using on-the-go soil sensors. In Precision Agriculture. Papers from the Fifth European Conference on Precision Agriculture, Uppsala, Sweden, 9–12 June 2005; Stafford, J., Ed.; Wageningen Academic Publishers: Wageningen, The Netherlands, 2005.
  26. Jonjak, A.K.; Adamchuk, V.I.; Wortmann, C.S.; Ferguson, R.B.; Shapiro, C.A. A comparison of conventional and sensor-based lime requirement maps. In Proceedings of the Tenth International Conference on Precision Agriculture, Denver, CO, USA, 18–21 July 2010; Khosla, R., Ed.; Colorado State University: Fort Collins, CL, USA, 2010.
  27. Sharma, U.C.; Singh, R.P. Acid soils of India: Their distribution, management and future strategies for higher productivity. Fertil. News 2002, 47, 45–48, 51–52.
  28. Schultz, A.; Wieland, R.; Lutze, G. Neural networks in agroecological modelling–stylish application or helpful tool? Comput. Electron. Agric. 2000, 29, 73–97.
  29. Pantazi, X.E.; Moshou, D.; Alexandridis, T.; Whetton, R.L.; Mouazen, A.M. Wheat yield prediction using machine learning and advanced sensing techniques. Comput. Electron. Agric. 2016, 124, 57–65.
  30. Padarian, J.; Minasny, B.; McBratney, A.B. Machine learning and soil sciences: A review aided by machine learning tools. Soil 2020, 6, 35–52.
  31. Viscarra Rossel, R.A.; Behrens, T. Using data mining to model and interpret soil diffuse reflectance spectra. Geoderma 2010, 158, 46–54.
  32. Shi, Z.; Ji, W.; Viscarra Rossel, R.A.; Chen, S.; Zhou, Y. Prediction of soil organic matter using a spatially constrained local partial least squares regression and the Chinese vis–NIR spectral library. Eur. J. Soil Sci. 2015, 66, 679–687.
  33. Yang, M.; Xu, D.; Chen, S.; Li, H.; Shi, Z. Evaluation of machine learning approaches to predict soil organic matter and pH using vis-NIR Spectra. Sensors 2019, 19, 263.
  34. Huang, G.; Zhu, Q.; Siew, C.K. Extreme learning machine: A new learning scheme of feedforward neural networks. In Proceedings of the 2004 IEEE International Joint Conference on Neural Networks, Budapest, Hungary, 25–29 July 2004.
  35. Lehmann, N.; Briner, S.; Finger, R. The impact of climate and price risks on agricultural land use and crop management decisions. Land Use Policy 2013, 35, 119–130.
  36. Bhattacharyya, R.; Ghosh, B.N.; Mishra, P.K.; Mandal, B.; Rao, C.S.; Sarkar, D.; Das, K.; Anil, K.S.; Lalitha, M.; Hati, K.M.; et al. Soil degradation in India: Challenges and potential solutions. Sustainability 2015, 7, 3528–3570.
  37. Shanwad, U.K.; Patil, V.C.; Gowda, H.H. Precision Farming: Dreams and Realities for Indian Agriculture. Available online: (accessed on 12 December 2021).
  38. FAO. Country Rank in the World, by commodity. Food and Agriculture Organization of the United Nations; FAO: Rome, Italy, 2011.
  39. FAO. Fertilizer Use by Crop in India. Food and Agriculture Organization of the United Nations; FAO: Rome, Italy, 2005.
  40. Siddiq, E.A. Yawning productivity gaps. In The Hindu Survey of Indian Agriculture; The Hindu: New Delhi, India, 2000; p. 43.
  41. Kalkat, G.S. Agriculture in India-II, Punjab Faces Post-Green Revolution Problems. Available online: (accessed on 12 December 2021).
  42. Mittal, S.; Kaur, G.; Vishwakarma, G.S. Effects of environmental pesticides on the health of rural communities in the Malwa region of Punjab, India: A Review. Hum. Ecol. Risk Assess. 2014, 20, 366–387.
  43. Yan, G.; Zhou, S.; Lian-qing, Z.; Xi, J.; Yan-feng, T.; Hong-fen, T. Integrating remote sensing and proximal sensors for the detection of soil moisture and salinity variability in coastal areas. J. Integr. Agric. 2013, 12, 723–731.
Subjects: Soil Science
Contributors MDPI registered users' name will be linked to their SciProfiles pages. To register with us, please refer to : , , , , , , , , , , , , , , , , , ,
View Times: 463
Revisions: 2 times (View History)
Update Date: 23 Aug 2022
Video Production Service