High-frequency monitoring of agrometeorological parameters is quintessential in the domain of Precision Agriculture (PA), where timeliness of collected observations and the ability to generate ahead-of-time predictions can substantially impact the crop yield. In this context, state-of-the-art internet-of-things (IoT)-based sensing platforms are often employed to generate, pre-process and assimilate real-time data from heterogeneous sensors and streaming data sources. Simultaneously, Time-Series Forecasting Algorithms (TSFAs) are responsible for generating reliable forecasts with a pre-defined forecast horizon and confidence. These TSFAs often rely on modelling the correlation between endogenous variables, the impact of exogenous variables on latent form and structural properties of data such as autocorrelation, periodicity, trend, pattern, and causality to approximate the model parameters. Traditionally, TSFAs such as the Holt–Winters (HW) and Autoregressive family of models (ARIMA) apply a linear and parametric approach towards model approximation, whilst models like Support Vector Regression (SVRs) and Neural Networks (NNs) adhere to a non-linear, non-parametric approach for modelling the historical data. Recently, Deep-Learning-based TSFAs such as Recurrent Neural Networks (RNNs), and Long-Short-Term-Memory (LSTMS) have gained popularity due to their capability to model long sequences of highly non-linear and stochastic data effectively. However, the evolution of TSFAs for predicting agrometeorological parameters pivots around one-step-ahead forecasting, which often overestimates the performance metrics defined for validating forecast capabilities of potential TSFAs. Hence, this paper attempts to evaluate and compare the performance of different machine learning (ML) and deep learning (DL) based TSFAs under one-step and multi-step-ahead forecast scenarios, thereby estimating the generalization capabilities of TSFA models over unseen data. The data used in this study are collected from an Automatic Weather Station (AWS), sampled at an interval of 15 min, and range over one month. Temperature (T) and Humidity (H) observations from the AWS are further converted into univariate, supervised time-series diurnal data profiles. Finally, walk-forward validation is used to evaluate recursive one-step-ahead forecasts until the desired prediction horizon is achieved. The results show that the Seasonal Auto-Regressive Integrated Moving Average (SARIMA) and SVR models outperform their DL-based counterparts in one-step and multi-step ahead settings with a fixed forecast horizon. This work aims to present a baseline comparison between different TSFAs to assist the process of model selection and facilitate rapid ahead-of-time forecasting for end-user applications.

Realization of agricultural crop condition through field survey is quite expensive, time consuming and sometimes not practical for remote locations. Optical remote sensing techniques can provide information on real condition of the crops by observing spectral reflectance at different crop growth phases and is less expensive and less time consuming. Hyperspectral remote sensing provides a unique opportunity for non-destructive, timely and accurate estimation of crop biophysical and biochemical properties. In this study, a field experiment was conducted to identify the water and nitrogen stress indicative spectral bands using ground-based hyperspectral data and to assess the predictive capability of selective bands on yield of maize under water and nitrogen stress environment. The experiment comprised of three irrigation scheduling treatments based on IW/CPE ration of 0.6, 0.8 and 1.2 and three nitrogen level treatments, i.e., 100, 200 and 300 kg of N ha⁻¹, respectively, with three replications in a split plot design. The spectral reflectance was measured before irrigation at tasseling and dough stage of the maize crop using portable field spectroradiometer. The results of stepwise multiple linear regression indicated the highest predicting capability of spectral bands 540 nm, 780 nm and 860 nm for leaf nitrogen and 700 nm, 740 nm and 860 nm for leaf water content. The derived biophysical parameters based on spectral reflectance viz. relative leaf water content (%), leaf area index and leaf nitrogen contentment (%) at tasseling stage of maize crop accounted for 80%, 61% and 66% variation in grain yield, respectively.